In this study, we propose a novel approach for RGB-D salient instance segmentation using a dual-branch cross-modal feature calibration architecture called CalibNet. Our method simultaneously calibrates depth and RGB features in the kernel and mask branches to generate instance-aware kernels and mask features. CalibNet consists of three simple modules, a dynamic interactive kernel (DIK) and a weight-sharing fusion (WSF), which work together to generate effective instance-aware kernels and integrate cross-modal features. To improve the quality of depth features, we incorporate a depth similarity assessment (DSA) module prior to DIK and WSF. In addition, we further contribute a new DSIS dataset, which contains 1,940 images with elaborate instance-level annotations. Extensive experiments on three challenging benchmarks show that CalibNet yields a promising result, i.e., 58.0% AP with $320times 480$ input size on the COME15K-E test set, which significantly surpasses the alternative frameworks. Our code and dataset will be publicly available at: https://github.com/PJLallen/CalibNet .
{"title":"CalibNet: Dual-Branch Cross-Modal Calibration for RGB-D Salient Instance Segmentation","authors":"Jialun Pei;Tao Jiang;He Tang;Nian Liu;Yueming Jin;Deng-Ping Fan;Pheng-Ann Heng","doi":"10.1109/TIP.2024.3432328","DOIUrl":"10.1109/TIP.2024.3432328","url":null,"abstract":"In this study, we propose a novel approach for RGB-D salient instance segmentation using a dual-branch cross-modal feature calibration architecture called CalibNet. Our method simultaneously calibrates depth and RGB features in the kernel and mask branches to generate instance-aware kernels and mask features. CalibNet consists of three simple modules, a dynamic interactive kernel (DIK) and a weight-sharing fusion (WSF), which work together to generate effective instance-aware kernels and integrate cross-modal features. To improve the quality of depth features, we incorporate a depth similarity assessment (DSA) module prior to DIK and WSF. In addition, we further contribute a new DSIS dataset, which contains 1,940 images with elaborate instance-level annotations. Extensive experiments on three challenging benchmarks show that CalibNet yields a promising result, i.e., 58.0% AP with \u0000<inline-formula> <tex-math>$320times 480$ </tex-math></inline-formula>\u0000 input size on the COME15K-E test set, which significantly surpasses the alternative frameworks. Our code and dataset will be publicly available at: \u0000<uri>https://github.com/PJLallen/CalibNet</uri>\u0000.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141794319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-29DOI: 10.1109/TIP.2024.3430539
Jialiang Tang;Ning Jiang;Hongyuan Zhu;Joey Tianyi Zhou;Chen Gong
Data-free knowledge distillation aims to learn a small student network from a large pre-trained teacher network without the aid of original training data. Recent works propose to gather alternative data from the Internet for training student network. In a more realistic scenario, the data on the Internet contains two types of label noise, namely: 1) closed-set label noise, where some examples belong to the known categories but are mislabeled; and 2) open-set label noise, where the true labels of some mislabeled examples are outside the known categories. However, the latter is largely ignored by existing works, leading to limited student network performance. Therefore, this paper proposes a novel data-free knowledge distillation paradigm by utilizing a webly-collected dataset under universal label noise, which means both closed-set and open-set label noise should be tackled. Specifically, we first split the collected noisy dataset into clean set, closed noisy set, and open noisy set based on the prediction uncertainty of various data types. For the closed-set noisy examples, their labels are refined by teacher network. Meanwhile, a noise-robust hybrid contrastive learning is performed on the clean set and refined closed noisy set to encourage student network to learn the categorical and instance knowledge inherited by teacher network. For the open-set noisy examples unexplored by previous work, we regard them as unlabeled and conduct self-supervised learning on them to enrich the supervision signal for student network. Intensive experimental results on image classification tasks demonstrate that our approach can achieve superior performance to state-of-the-art data-free knowledge distillation methods.
{"title":"Learning Student Network Under Universal Label Noise","authors":"Jialiang Tang;Ning Jiang;Hongyuan Zhu;Joey Tianyi Zhou;Chen Gong","doi":"10.1109/TIP.2024.3430539","DOIUrl":"10.1109/TIP.2024.3430539","url":null,"abstract":"Data-free knowledge distillation aims to learn a small student network from a large pre-trained teacher network without the aid of original training data. Recent works propose to gather alternative data from the Internet for training student network. In a more realistic scenario, the data on the Internet contains two types of label noise, namely: 1) closed-set label noise, where some examples belong to the known categories but are mislabeled; and 2) open-set label noise, where the true labels of some mislabeled examples are outside the known categories. However, the latter is largely ignored by existing works, leading to limited student network performance. Therefore, this paper proposes a novel data-free knowledge distillation paradigm by utilizing a webly-collected dataset under universal label noise, which means both closed-set and open-set label noise should be tackled. Specifically, we first split the collected noisy dataset into clean set, closed noisy set, and open noisy set based on the prediction uncertainty of various data types. For the closed-set noisy examples, their labels are refined by teacher network. Meanwhile, a noise-robust hybrid contrastive learning is performed on the clean set and refined closed noisy set to encourage student network to learn the categorical and instance knowledge inherited by teacher network. For the open-set noisy examples unexplored by previous work, we regard them as unlabeled and conduct self-supervised learning on them to enrich the supervision signal for student network. Intensive experimental results on image classification tasks demonstrate that our approach can achieve superior performance to state-of-the-art data-free knowledge distillation methods.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141794320","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-26DOI: 10.1109/TIP.2024.3426469
Zengyu Wan, Yang Wang, Zhai Wei, Ganchao Tan, Yang Cao, Zheng-Jun Zha
Event cameras respond to temporal dynamics, helping to resolve ambiguities in spatio-temporal changes for optical flow estimation. However, the unique spatio-temporal event distribution challenges the feature extraction, and the direct construction of motion representation through the orthogonal view is less than ideal due to the entanglement of appearance and motion. This paper proposes to transform the orthogonal view into a motion-dependent one for enhancing event-based motion representation and presents a Motion View-based Network (MV-Net) for practical optical flow estimation. Specifically, this motion-dependent view transformation is achieved through the Event View Transformation Module, which captures the relationship between the steepest temporal changes and motion direction, incorporating these temporal cues into the view transformation process for feature gathering. This module includes two phases: extracting the temporal evolution clues by central difference operation in the extraction phase and capturing the motion pattern by evolution-guided deformable convolution in the perception phase. Besides, the MV-Net constructs an eccentric downsampling process to avoid response weakening from the sparsity of events in the downsampling stage. The whole network is trained end-to-end in a self-supervised manner, and the evaluations conducted on four challenging datasets reveal the superior performance of the proposed model compared to state-of-the-art (SOTA) methods.
{"title":"Event-based Optical Flow via Transforming into Motion-dependent View.","authors":"Zengyu Wan, Yang Wang, Zhai Wei, Ganchao Tan, Yang Cao, Zheng-Jun Zha","doi":"10.1109/TIP.2024.3426469","DOIUrl":"https://doi.org/10.1109/TIP.2024.3426469","url":null,"abstract":"<p><p>Event cameras respond to temporal dynamics, helping to resolve ambiguities in spatio-temporal changes for optical flow estimation. However, the unique spatio-temporal event distribution challenges the feature extraction, and the direct construction of motion representation through the orthogonal view is less than ideal due to the entanglement of appearance and motion. This paper proposes to transform the orthogonal view into a motion-dependent one for enhancing event-based motion representation and presents a Motion View-based Network (MV-Net) for practical optical flow estimation. Specifically, this motion-dependent view transformation is achieved through the Event View Transformation Module, which captures the relationship between the steepest temporal changes and motion direction, incorporating these temporal cues into the view transformation process for feature gathering. This module includes two phases: extracting the temporal evolution clues by central difference operation in the extraction phase and capturing the motion pattern by evolution-guided deformable convolution in the perception phase. Besides, the MV-Net constructs an eccentric downsampling process to avoid response weakening from the sparsity of events in the downsampling stage. The whole network is trained end-to-end in a self-supervised manner, and the evaluations conducted on four challenging datasets reveal the superior performance of the proposed model compared to state-of-the-art (SOTA) methods.</p>","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141768324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-26DOI: 10.1109/TIP.2024.3430073
Baoxing Li;Yong Deng;Yehui Yang;Xu Zhao
To reconstruct a 3D human surface from a single image, it is crucial to simultaneously consider human pose, shape, and clothing details. Recent approaches have combined parametric body models (such as SMPL), which capture body pose and shape priors, with neural implicit functions that flexibly learn clothing details. However, this combined representation introduces additional computation, e.g. signed distance calculation in 3D body feature extraction, leading to redundancy in the implicit query-and-infer process and failing to preserve the underlying body shape prior. To address these issues, we propose a novel IUVD-Feedback representation, consisting of an IUVD occupancy function and a feedback query algorithm. This representation replaces the time-consuming signed distance calculation with a simple linear transformation in the IUVD space, leveraging the SMPL UV maps. Additionally, it reduces redundant query points through a feedback mechanism, leading to more reasonable 3D body features and more effective query points, thereby preserving the parametric body prior. Moreover, the IUVD-Feedback representation can be embedded into any existing implicit human reconstruction pipeline without requiring modifications to the trained neural networks. Experiments on the THuman2.0 dataset demonstrate that the proposed IUVD-Feedback representation improves the robustness of results and achieves three times faster acceleration in the query-and-infer process. Furthermore, this representation holds potential for generative applications by leveraging its inherent semantic information from the parametric body model.
{"title":"An Embeddable Implicit IUVD Representation for Part-Based 3D Human Surface Reconstruction","authors":"Baoxing Li;Yong Deng;Yehui Yang;Xu Zhao","doi":"10.1109/TIP.2024.3430073","DOIUrl":"10.1109/TIP.2024.3430073","url":null,"abstract":"To reconstruct a 3D human surface from a single image, it is crucial to simultaneously consider human pose, shape, and clothing details. Recent approaches have combined parametric body models (such as SMPL), which capture body pose and shape priors, with neural implicit functions that flexibly learn clothing details. However, this combined representation introduces additional computation, e.g. signed distance calculation in 3D body feature extraction, leading to redundancy in the implicit query-and-infer process and failing to preserve the underlying body shape prior. To address these issues, we propose a novel IUVD-Feedback representation, consisting of an IUVD occupancy function and a feedback query algorithm. This representation replaces the time-consuming signed distance calculation with a simple linear transformation in the IUVD space, leveraging the SMPL UV maps. Additionally, it reduces redundant query points through a feedback mechanism, leading to more reasonable 3D body features and more effective query points, thereby preserving the parametric body prior. Moreover, the IUVD-Feedback representation can be embedded into any existing implicit human reconstruction pipeline without requiring modifications to the trained neural networks. Experiments on the THuman2.0 dataset demonstrate that the proposed IUVD-Feedback representation improves the robustness of results and achieves three times faster acceleration in the query-and-infer process. Furthermore, this representation holds potential for generative applications by leveraging its inherent semantic information from the parametric body model.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141768323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Brain region-of-interest (ROI) segmentation with magnetic resonance (MR) images is a basic prerequisite step for brain analysis. The main problem with using deep learning for brain ROI segmentation is the lack of sufficient annotated data. To address this issue, in this paper, we propose a simple multi-atlas supervised contrastive learning framework (MAS-CL) for brain ROI segmentation with MR images in an end-to-end manner. Specifically, our MAS-CL framework mainly consists of two steps, including 1) a multi-atlas supervised contrastive learning method to learn the latent representation using a limited amount of voxel-level labeling brain MR images, and 2) brain ROI segmentation based on the pre-trained backbone using our MSA-CL method. Specifically, different from traditional contrastive learning, in our proposed method, we use multi-atlas supervised information to pre-train the backbone for learning the latent representation of input MR image, i.e., the correlation of each sample pair is defined by using the label maps of input MR image and atlas images. Then, we extend the pre-trained backbone to segment brain ROI with MR images. We perform our proposed MAS-CL framework with five segmentation methods on LONI-LPBA40, IXI, OASIS, ADNI, and CC359 datasets for brain ROI segmentation with MR images. Various experimental results suggested that our proposed MAS-CL framework can significantly improve the segmentation performance on these five datasets.
磁共振（MR）图像的脑兴趣区（ROI）分割是脑分析的基本前提步骤。使用深度学习进行脑兴趣区分割的主要问题是缺乏足够的注释数据。为了解决这个问题，我们在本文中提出了一个简单的多图谱监督对比学习框架（MAS-CL），用于以端到端的方式对磁共振图像进行大脑 ROI 分割。具体来说，我们的 MAS-CL 框架主要包括两个步骤：1）利用有限的体素级标注脑部 MR 图像，采用多图谱监督对比学习方法学习潜表征；2）利用我们的 MSA-CL 方法，基于预训练的骨干进行脑部 ROI 分割。具体来说，与传统的对比学习不同，在我们提出的方法中，我们使用多图集监督信息来预训练骨干，以学习输入 MR 图像的潜表征，即使用输入 MR 图像和图集图像的标签图来定义每个样本对的相关性。然后，我们将预先训练好的反骨干扩展到用磁共振图像分割大脑 ROI。我们在 LONI-LPBA40、IXI、OASIS、ADNI 和 CC359 数据集上使用我们提出的 MAS-CL 框架和五种分割方法对磁共振图像进行脑 ROI 分割。各种实验结果表明，我们提出的 MAS-CL 框架能显著提高这五个数据集的分割性能。
{"title":"MAS-CL: An End-to-End Multi-Atlas Supervised Contrastive Learning Framework for Brain ROI Segmentation","authors":"Liang Sun;Yanling Fu;Junyong Zhao;Wei Shao;Qi Zhu;Daoqiang Zhang","doi":"10.1109/TIP.2024.3431451","DOIUrl":"10.1109/TIP.2024.3431451","url":null,"abstract":"Brain region-of-interest (ROI) segmentation with magnetic resonance (MR) images is a basic prerequisite step for brain analysis. The main problem with using deep learning for brain ROI segmentation is the lack of sufficient annotated data. To address this issue, in this paper, we propose a simple multi-atlas supervised contrastive learning framework (MAS-CL) for brain ROI segmentation with MR images in an end-to-end manner. Specifically, our MAS-CL framework mainly consists of two steps, including 1) a multi-atlas supervised contrastive learning method to learn the latent representation using a limited amount of voxel-level labeling brain MR images, and 2) brain ROI segmentation based on the pre-trained backbone using our MSA-CL method. Specifically, different from traditional contrastive learning, in our proposed method, we use multi-atlas supervised information to pre-train the backbone for learning the latent representation of input MR image, i.e., the correlation of each sample pair is defined by using the label maps of input MR image and atlas images. Then, we extend the pre-trained backbone to segment brain ROI with MR images. We perform our proposed MAS-CL framework with five segmentation methods on LONI-LPBA40, IXI, OASIS, ADNI, and CC359 datasets for brain ROI segmentation with MR images. Various experimental results suggested that our proposed MAS-CL framework can significantly improve the segmentation performance on these five datasets.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141763553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-24DOI: 10.1109/TIP.2024.3430532
Zhiying Jiang;Zengxi Zhang;Jinyuan Liu;Xin Fan;Risheng Liu
Image stitching is a critical task in panorama perception that involves combining images captured from different viewing positions to reconstruct a wider field-of-view (FOV) image. Existing visible image stitching methods suffer from performance drops under severe conditions since environmental factors can easily impair visible images. In contrast, infrared images possess greater penetrating ability and are less affected by environmental factors. Therefore, we propose an infrared and visible image-based multispectral image stitching method to achieve all-weather, broad FOV scene perception. Specifically, based on two pairs of infrared and visible images, we employ the salient structural information from the infrared images and the textual details from the visible images to infer the correspondences within different modality-specific features. For this purpose, a multiscale progressive mechanism coupled with quadrature correlation is exploited to improve regression in different modalities. Exploiting the complementary properties, accurate and credible homography can be obtained by integrating the deformation parameters of the two modalities to compensate for the missing modality-specific information. A global-aware guided reconstruction module is established to generate an informative and broad scene, wherein the attentive features of different viewpoints are introduced to fuse the source images with a more seamless and comprehensive appearance. We construct a high-quality infrared and visible stitching dataset for evaluation, including real-world and synthetic sets. The qualitative and quantitative results demonstrate that the proposed method outperforms the intuitive cascaded fusion-stitching procedure, achieving more robust and credible panorama generation. Code and dataset are available at https://github.com/Jzy2017/MSGA .
{"title":"Multispectral Image Stitching via Global-Aware Quadrature Pyramid Regression","authors":"Zhiying Jiang;Zengxi Zhang;Jinyuan Liu;Xin Fan;Risheng Liu","doi":"10.1109/TIP.2024.3430532","DOIUrl":"10.1109/TIP.2024.3430532","url":null,"abstract":"Image stitching is a critical task in panorama perception that involves combining images captured from different viewing positions to reconstruct a wider field-of-view (FOV) image. Existing visible image stitching methods suffer from performance drops under severe conditions since environmental factors can easily impair visible images. In contrast, infrared images possess greater penetrating ability and are less affected by environmental factors. Therefore, we propose an infrared and visible image-based multispectral image stitching method to achieve all-weather, broad FOV scene perception. Specifically, based on two pairs of infrared and visible images, we employ the salient structural information from the infrared images and the textual details from the visible images to infer the correspondences within different modality-specific features. For this purpose, a multiscale progressive mechanism coupled with quadrature correlation is exploited to improve regression in different modalities. Exploiting the complementary properties, accurate and credible homography can be obtained by integrating the deformation parameters of the two modalities to compensate for the missing modality-specific information. A global-aware guided reconstruction module is established to generate an informative and broad scene, wherein the attentive features of different viewpoints are introduced to fuse the source images with a more seamless and comprehensive appearance. We construct a high-quality infrared and visible stitching dataset for evaluation, including real-world and synthetic sets. The qualitative and quantitative results demonstrate that the proposed method outperforms the intuitive cascaded fusion-stitching procedure, achieving more robust and credible panorama generation. Code and dataset are available at \u0000<uri>https://github.com/Jzy2017/MSGA</uri>\u0000.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141754775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recent advances in bio-inspired vision with event cameras and associated spiking neural networks (SNNs) have provided promising solutions for low-power consumption neuromorphic tasks. However, as the research of event cameras is still in its infancy, the amount of labeled event stream data is much less than that of the RGB database. The traditional method of converting static images into event streams by simulation to increase the sample size cannot simulate the characteristics of event cameras such as high temporal resolution. To take advantage of both the rich knowledge in labeled RGB images and the features of the event camera, we propose a transfer learning method from the RGB to the event domain in this paper. Specifically, we first introduce a transfer learning framework named R2ETL (RGB to Event Transfer Learning), including a novel encoding alignment module and a feature alignment module. Then, we introduce the temporal centered kernel alignment (TCKA) loss function to improve the efficiency of transfer learning. It aligns the distribution of temporal neuron states by adding a temporal learning constraint. Finally, we theoretically analyze the amount of data required by the deep neuromorphic model to prove the necessity of our method. Numerous experiments demonstrate that our proposed framework outperforms the state-of-the-art SNN and artificial neural network (ANN) models trained on event streams, including N-MNIST, CIFAR10-DVS and N-Caltech101. This indicates that the R2ETL framework is able to leverage the knowledge of labeled RGB images to help the training of SNN on event streams.
{"title":"Spiking Transfer Learning From RGB Image to Neuromorphic Event Stream","authors":"Qiugang Zhan;Guisong Liu;Xiurui Xie;Ran Tao;Malu Zhang;Huajin Tang","doi":"10.1109/TIP.2024.3430043","DOIUrl":"10.1109/TIP.2024.3430043","url":null,"abstract":"Recent advances in bio-inspired vision with event cameras and associated spiking neural networks (SNNs) have provided promising solutions for low-power consumption neuromorphic tasks. However, as the research of event cameras is still in its infancy, the amount of labeled event stream data is much less than that of the RGB database. The traditional method of converting static images into event streams by simulation to increase the sample size cannot simulate the characteristics of event cameras such as high temporal resolution. To take advantage of both the rich knowledge in labeled RGB images and the features of the event camera, we propose a transfer learning method from the RGB to the event domain in this paper. Specifically, we first introduce a transfer learning framework named R2ETL (RGB to Event Transfer Learning), including a novel encoding alignment module and a feature alignment module. Then, we introduce the temporal centered kernel alignment (TCKA) loss function to improve the efficiency of transfer learning. It aligns the distribution of temporal neuron states by adding a temporal learning constraint. Finally, we theoretically analyze the amount of data required by the deep neuromorphic model to prove the necessity of our method. Numerous experiments demonstrate that our proposed framework outperforms the state-of-the-art SNN and artificial neural network (ANN) models trained on event streams, including N-MNIST, CIFAR10-DVS and N-Caltech101. This indicates that the R2ETL framework is able to leverage the knowledge of labeled RGB images to help the training of SNN on event streams.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141753572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-23DOI: 10.1109/TIP.2024.3430080
Wenrui Li;Penghong Wang;Ruiqin Xiong;Xiaopeng Fan
The spiking neural networks (SNNs) that efficiently encode temporal sequences have shown great potential in extracting audio-visual joint feature representations. However, coupling SNNs (binary spike sequences) with transformers (float-point sequences) to jointly explore the temporal-semantic information still facing challenges. In this paper, we introduce a novel Spiking Tucker Fusion Transformer (STFT) for audio-visual zero-shot learning (ZSL). The STFT leverage the temporal and semantic information from different time steps to generate robust representations. The time-step factor (TSF) is introduced to dynamically synthesis the subsequent inference information. To guide the formation of input membrane potentials and reduce the spike noise, we propose a global-local pooling (GLP) which combines the max and average pooling operations. Furthermore, the thresholds of the spiking neurons are dynamically adjusted based on semantic and temporal cues. Integrating the temporal and semantic information extracted by SNNs and Transformers are difficult due to the increased number of parameters in a straightforward bilinear model. To address this, we introduce a temporal-semantic Tucker fusion module, which achieves multi-scale fusion of SNN and Transformer outputs while maintaining full second-order interactions. Our experimental results demonstrate the effectiveness of the proposed approach in achieving state-of-the-art performance in three benchmark datasets. The harmonic mean (HM) improvement of VGGSound, UCF101 and ActivityNet are around 15.4%, 3.9%, and 14.9%, respectively.
{"title":"Spiking Tucker Fusion Transformer for Audio-Visual Zero-Shot Learning","authors":"Wenrui Li;Penghong Wang;Ruiqin Xiong;Xiaopeng Fan","doi":"10.1109/TIP.2024.3430080","DOIUrl":"10.1109/TIP.2024.3430080","url":null,"abstract":"The spiking neural networks (SNNs) that efficiently encode temporal sequences have shown great potential in extracting audio-visual joint feature representations. However, coupling SNNs (binary spike sequences) with transformers (float-point sequences) to jointly explore the temporal-semantic information still facing challenges. In this paper, we introduce a novel Spiking Tucker Fusion Transformer (STFT) for audio-visual zero-shot learning (ZSL). The STFT leverage the temporal and semantic information from different time steps to generate robust representations. The time-step factor (TSF) is introduced to dynamically synthesis the subsequent inference information. To guide the formation of input membrane potentials and reduce the spike noise, we propose a global-local pooling (GLP) which combines the max and average pooling operations. Furthermore, the thresholds of the spiking neurons are dynamically adjusted based on semantic and temporal cues. Integrating the temporal and semantic information extracted by SNNs and Transformers are difficult due to the increased number of parameters in a straightforward bilinear model. To address this, we introduce a temporal-semantic Tucker fusion module, which achieves multi-scale fusion of SNN and Transformer outputs while maintaining full second-order interactions. Our experimental results demonstrate the effectiveness of the proposed approach in achieving state-of-the-art performance in three benchmark datasets. The harmonic mean (HM) improvement of VGGSound, UCF101 and ActivityNet are around 15.4%, 3.9%, and 14.9%, respectively.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141753573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-19DOI: 10.1109/TIP.2024.3428316
Tianlu Zhang;Qiang Jiao;Qiang Zhang;Jungong Han
In RGB-T tracking, there exist rich spatial relationships between the target and backgrounds within multi-modal data as well as sound consistencies of spatial relationships among successive frames, which are crucial for boosting the tracking performance. However, most existing RGB-T trackers overlook such multi-modal spatial relationships and temporal consistencies within RGB-T videos, hindering them from robust tracking and practical applications in complex scenarios. In this paper, we propose a novel Multi-modal Spatial-Temporal Context (MMSTC) network for RGB-T tracking, which employs a Transformer architecture for the construction of reliable multi-modal spatial context information and the effective propagation of temporal context information. Specifically, a Multi-modal Transformer Encoder (MMTE) is designed to achieve the encoding of reliable multi-modal spatial contexts as well as the fusion of multi-modal features. Furthermore, a Quality-aware Transformer Decoder (QATD) is proposed to effectively propagate the tracking cues from historical frames to the current frame, which facilitates the object searching process. Moreover, the proposed MMSTC network can be easily extended to various tracking frameworks. New state-of-the-art results on five prevalent RGB-T tracking benchmarks demonstrate the superiorities of our proposed trackers over existing ones.
{"title":"Exploring Multi-Modal Spatial–Temporal Contexts for High-Performance RGB-T Tracking","authors":"Tianlu Zhang;Qiang Jiao;Qiang Zhang;Jungong Han","doi":"10.1109/TIP.2024.3428316","DOIUrl":"10.1109/TIP.2024.3428316","url":null,"abstract":"In RGB-T tracking, there exist rich spatial relationships between the target and backgrounds within multi-modal data as well as sound consistencies of spatial relationships among successive frames, which are crucial for boosting the tracking performance. However, most existing RGB-T trackers overlook such multi-modal spatial relationships and temporal consistencies within RGB-T videos, hindering them from robust tracking and practical applications in complex scenarios. In this paper, we propose a novel Multi-modal Spatial-Temporal Context (MMSTC) network for RGB-T tracking, which employs a Transformer architecture for the construction of reliable multi-modal spatial context information and the effective propagation of temporal context information. Specifically, a Multi-modal Transformer Encoder (MMTE) is designed to achieve the encoding of reliable multi-modal spatial contexts as well as the fusion of multi-modal features. Furthermore, a Quality-aware Transformer Decoder (QATD) is proposed to effectively propagate the tracking cues from historical frames to the current frame, which facilitates the object searching process. Moreover, the proposed MMSTC network can be easily extended to various tracking frameworks. New state-of-the-art results on five prevalent RGB-T tracking benchmarks demonstrate the superiorities of our proposed trackers over existing ones.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141728471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-15DOI: 10.1109/TIP.2024.3424335
Hao Chang;Peijin Wang;Wenhui Diao;Guangluan Xu;Xian Sun
Recently, the transformer has achieved notable success in remote sensing (RS) change detection (CD). Its outstanding long-distance modeling ability can effectively recognize the change of interest (CoI). However, in order to obtain the precise pixel-level change regions, many methods directly integrate the stacked transformer blocks into the UNet-style structure, which causes the high computation costs. Besides, the existing methods generally consider bitemporal or differential features separately, which makes the utilization of ground semantic information still insufficient. In this paper, we propose the multiscale dual-space interactive perception network (MDIPNet) to fill these two gaps. On the one hand, we simplify the stacked multi-head transformer blocks into the single-layer single-head attention module and further introduce the lightweight parallel fusion module (LPFM) to perform the efficient information integration. On the other hand, based on the simplified attention mechanism, we propose the cross-space perception module (CSPM) to connect the bitemporal and differential feature spaces, which can help our model suppress the pseudo changes and mine the more abundant semantic consistency of CoI. Extensive experiment results on three challenging datasets and one urban expansion scene indicate that compared with the mainstream CD methods, our MDIPNet obtains the state-of-the-art (SOTA) performance while further controlling the computation costs.
最近，变压器在遥感（RS）变化探测（CD）方面取得了显著的成功。其出色的远距离建模能力可以有效识别感兴趣的变化（CoI）。然而，为了获得精确的像素级变化区域，许多方法直接将堆叠的变换器块集成到 UNet 样式的结构中，导致计算成本较高。此外，现有方法一般都是单独考虑位时或差分特征，对地面语义信息的利用还不够充分。本文提出了多尺度双空间交互感知网络（MDIPNet）来填补这两个空白。一方面，我们将堆叠的多头变换模块简化为单层单头注意模块，并进一步引入轻量级并行融合模块（LPFM），以实现高效的信息整合。另一方面，在简化注意力机制的基础上，我们提出了跨空间感知模块（CSPM）来连接位时特征空间和差分特征空间，这可以帮助我们的模型抑制伪变化，挖掘出更丰富的CoI语义一致性。在三个具有挑战性的数据集和一个城市扩张场景上的大量实验结果表明，与主流的 CD 方法相比，我们的 MDIPNet 在进一步控制计算成本的同时，获得了最先进的性能（SOTA）。
{"title":"Remote Sensing Change Detection With Bitemporal and Differential Feature Interactive Perception","authors":"Hao Chang;Peijin Wang;Wenhui Diao;Guangluan Xu;Xian Sun","doi":"10.1109/TIP.2024.3424335","DOIUrl":"10.1109/TIP.2024.3424335","url":null,"abstract":"Recently, the transformer has achieved notable success in remote sensing (RS) change detection (CD). Its outstanding long-distance modeling ability can effectively recognize the change of interest (CoI). However, in order to obtain the precise pixel-level change regions, many methods directly integrate the stacked transformer blocks into the UNet-style structure, which causes the high computation costs. Besides, the existing methods generally consider bitemporal or differential features separately, which makes the utilization of ground semantic information still insufficient. In this paper, we propose the multiscale dual-space interactive perception network (MDIPNet) to fill these two gaps. On the one hand, we simplify the stacked multi-head transformer blocks into the single-layer single-head attention module and further introduce the lightweight parallel fusion module (LPFM) to perform the efficient information integration. On the other hand, based on the simplified attention mechanism, we propose the cross-space perception module (CSPM) to connect the bitemporal and differential feature spaces, which can help our model suppress the pseudo changes and mine the more abundant semantic consistency of CoI. Extensive experiment results on three challenging datasets and one urban expansion scene indicate that compared with the mainstream CD methods, our MDIPNet obtains the state-of-the-art (SOTA) performance while further controlling the computation costs.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141621991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：