Pub Date : 2022-06-01DOI: 10.1109/CVPR52688.2022.00235
Banghuai Li
General object detectors are always evaluated on hand-designed datasets, e.g., MS COCO and Pascal VOC, which tend to maintain balanced data distribution over different classes. However, it goes against the practical applications in the real world which suffer from a heavy class imbalance problem, known as the long-tailed object detection. In this paper, we propose a novel method, named Adaptive Hierarchical Representation Learning (AHRL), from a metric learning perspective to address long-tailed object detection. We visualize each learned class representation in the feature space, and observe that some classes, especially under-represented scarce classes, are prone to cluster with analogous ones due to the lack of discriminative representation. Inspired by this, we propose to split the whole feature space into a hierarchical structure and eliminate the problem in a coarse-to-fine way. AHRL contains a two-stage training paradigm. First, we train a normal baseline model and construct the hierarchical structure under the unsupervised clustering method. Then, we design an AHR loss that consists of two optimization objectives. On the one hand, AHR loss retains the hierarchical structure and keeps representation clusters away from each other. On the other hand, AHR loss adopts adaptive margins according to specific class pairs in the same cluster to further optimize locally. We conduct extensive experiments on the challenging LVIS dataset and AHRL outperforms all the existing state-of-the-art methods, with 29.1% segmentation AP and 29.3% box AP on LVIS v0.5 and 27.6% segmentation AP and 28.7% box AP on LVIS v1.0 based on ResNet-101. We hope our simple yet effective approach will serve as a solid baseline to help stimulate future research in long-tailed object detection. Code will be released soon
{"title":"Adaptive Hierarchical Representation Learning for Long-Tailed Object Detection","authors":"Banghuai Li","doi":"10.1109/CVPR52688.2022.00235","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.00235","url":null,"abstract":"General object detectors are always evaluated on hand-designed datasets, e.g., MS COCO and Pascal VOC, which tend to maintain balanced data distribution over different classes. However, it goes against the practical applications in the real world which suffer from a heavy class imbalance problem, known as the long-tailed object detection. In this paper, we propose a novel method, named Adaptive Hierarchical Representation Learning (AHRL), from a metric learning perspective to address long-tailed object detection. We visualize each learned class representation in the feature space, and observe that some classes, especially under-represented scarce classes, are prone to cluster with analogous ones due to the lack of discriminative representation. Inspired by this, we propose to split the whole feature space into a hierarchical structure and eliminate the problem in a coarse-to-fine way. AHRL contains a two-stage training paradigm. First, we train a normal baseline model and construct the hierarchical structure under the unsupervised clustering method. Then, we design an AHR loss that consists of two optimization objectives. On the one hand, AHR loss retains the hierarchical structure and keeps representation clusters away from each other. On the other hand, AHR loss adopts adaptive margins according to specific class pairs in the same cluster to further optimize locally. We conduct extensive experiments on the challenging LVIS dataset and AHRL outperforms all the existing state-of-the-art methods, with 29.1% segmentation AP and 29.3% box AP on LVIS v0.5 and 27.6% segmentation AP and 28.7% box AP on LVIS v1.0 based on ResNet-101. We hope our simple yet effective approach will serve as a solid baseline to help stimulate future research in long-tailed object detection. Code will be released soon","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"51 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114040385","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}
Videos typically record the streaming and continuous visual data as discrete consecutive frames. Since the storage cost is expensive for videos of high fidelity, most of them are stored in a relatively low resolution and frame rate. Recent works of Space-Time Video Super-Resolution (STVSR) are developed to incorporate temporal interpolation and spatial super-resolution in a unified framework. However, most of them only support a fixed up-sampling scale, which limits their flexibility and applications. In this work, instead of following the discrete representations, we propose Video Implicit Neural Representation (VideoINR), and we show its applications for STVSR. The learned implicit neural representation can be decoded to videos of arbitrary spatial resolution and frame rate. We show that VideoINR achieves competitive performances with state-of-the-art STVSR methods on common up-sampling scales and significantly outperforms prior works on continuous and out-of-training-distribution scales. Our project page is at here and code is available at https://github.com/Picsart-AI-Research/VideoINR-Continuous-Space-Time-Super-Resolution.
{"title":"VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution","authors":"Zeyuan Chen, Yinbo Chen, Jingwen Liu, Xingqian Xu, Vidit Goel, Zhangyang Wang, Humphrey Shi, Xiaolong Wang","doi":"10.1109/CVPR52688.2022.00209","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.00209","url":null,"abstract":"Videos typically record the streaming and continuous visual data as discrete consecutive frames. Since the storage cost is expensive for videos of high fidelity, most of them are stored in a relatively low resolution and frame rate. Recent works of Space-Time Video Super-Resolution (STVSR) are developed to incorporate temporal interpolation and spatial super-resolution in a unified framework. However, most of them only support a fixed up-sampling scale, which limits their flexibility and applications. In this work, instead of following the discrete representations, we propose Video Implicit Neural Representation (VideoINR), and we show its applications for STVSR. The learned implicit neural representation can be decoded to videos of arbitrary spatial resolution and frame rate. We show that VideoINR achieves competitive performances with state-of-the-art STVSR methods on common up-sampling scales and significantly outperforms prior works on continuous and out-of-training-distribution scales. Our project page is at here and code is available at https://github.com/Picsart-AI-Research/VideoINR-Continuous-Space-Time-Super-Resolution.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"9 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114136258","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 : 2022-06-01DOI: 10.1109/CVPR52688.2022.00625
Che Sun, Yunde Jia, Yimin Guo, Yuwei Wu
We propose a novel method of registering less-overlap RGB-D scans. Our method learns global information of a scene to construct a panorama, and aligns RGB-D scans to the panorama to perform registration. Different from existing methods that use local feature points to register less-overlap RGB-D scans and mismatch too much, we use global information to guide the registration, thereby allevi-ating the mismatching problem by preserving global consis-tency of alignments. To this end, we build a scene inference network to construct the panorama representing global in-formation. We introduce a reinforcement learning strategy to iteratively align RGB-D scans with the panorama and re-fine the panorama representation, which reduces the noise of global information and preserves global consistency of both geometric and photometric alignments. Experimental results on benchmark datasets including SUNCG, Matterport, and ScanNet show the superiority of our method.
{"title":"Global-Aware Registration of Less-Overlap RGB-D Scans","authors":"Che Sun, Yunde Jia, Yimin Guo, Yuwei Wu","doi":"10.1109/CVPR52688.2022.00625","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.00625","url":null,"abstract":"We propose a novel method of registering less-overlap RGB-D scans. Our method learns global information of a scene to construct a panorama, and aligns RGB-D scans to the panorama to perform registration. Different from existing methods that use local feature points to register less-overlap RGB-D scans and mismatch too much, we use global information to guide the registration, thereby allevi-ating the mismatching problem by preserving global consis-tency of alignments. To this end, we build a scene inference network to construct the panorama representing global in-formation. We introduce a reinforcement learning strategy to iteratively align RGB-D scans with the panorama and re-fine the panorama representation, which reduces the noise of global information and preserves global consistency of both geometric and photometric alignments. Experimental results on benchmark datasets including SUNCG, Matterport, and ScanNet show the superiority of our method.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114189985","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 : 2022-06-01DOI: 10.1109/CVPR52688.2022.00990
Wenke Huang, Mang Ye, Bo Du
Federated learning has emerged as an important distributed learning paradigm, which normally involves collaborative updating with others and local updating on private data. However, heterogeneity problem and catastrophic forgetting bring distinctive challenges. First, due to non-i.i.d (identically and independently distributed) data and heterogeneous architectures, models suffer performance degradation on other domains and communication barrier with participants models. Second, in local updating, model is separately optimized on private data, which is prone to overfit current data distribution and forgets previously acquired knowledge, resulting in catastrophic forgetting. In this work, we propose FCCL (Federated CrossCorrelation and Continual Learning). For heterogeneity problem, FCCL leverages unlabeled public data for communication and construct cross-correlation matrix to learn a generalizable representation under domain shift. Mean- while, for catastrophic forgetting, FCCL utilizes knowledge distillation in local updating, providing inter and intra domain information without leaking privacy. Empirical results on various image classification tasks demonstrate the effectiveness of our method and the efficiency of modules.
{"title":"Learn from Others and Be Yourself in Heterogeneous Federated Learning","authors":"Wenke Huang, Mang Ye, Bo Du","doi":"10.1109/CVPR52688.2022.00990","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.00990","url":null,"abstract":"Federated learning has emerged as an important distributed learning paradigm, which normally involves collaborative updating with others and local updating on private data. However, heterogeneity problem and catastrophic forgetting bring distinctive challenges. First, due to non-i.i.d (identically and independently distributed) data and heterogeneous architectures, models suffer performance degradation on other domains and communication barrier with participants models. Second, in local updating, model is separately optimized on private data, which is prone to overfit current data distribution and forgets previously acquired knowledge, resulting in catastrophic forgetting. In this work, we propose FCCL (Federated CrossCorrelation and Continual Learning). For heterogeneity problem, FCCL leverages unlabeled public data for communication and construct cross-correlation matrix to learn a generalizable representation under domain shift. Mean- while, for catastrophic forgetting, FCCL utilizes knowledge distillation in local updating, providing inter and intra domain information without leaking privacy. Empirical results on various image classification tasks demonstrate the effectiveness of our method and the efficiency of modules.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114287636","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 : 2022-06-01DOI: 10.1109/CVPR52688.2022.01733
Felipe Gutierrez-Barragan, A. Ingle, T. Seets, Mohit Gupta, A. Velten
Single-photon avalanche diodes (SPADs) are an emerging pixel technology for time-of-flight (ToF) 3D cameras that can capture the time-of-arrival of individual photons at picosecond resolution. To estimate depths, current SPAD-based 3D cameras measure the round-trip time of a laser pulse by building a per-pixel histogram of photon times-tamps. As the spatial and timestamp resolution of SPAD-based cameras increase, their output data rates far exceed the capacity of existing data transfer technologies. One major reason for SPAD's bandwidth-intensive operation is the tight coupling that exists between depth resolution and histogram resolution. To weaken this coupling, we propose compressive single-photon histograms (CSPH). CSPHs are a per-pixel compressive representation of the high-resolution histogram, that is built on-the-fly, as each photon is detected. They are based on a family of linear coding schemes that can be expressed as a simple matrix operation. We design different CSPH coding schemes for 3D imaging and evaluate them under different signal and background levels, laser waveforms, and illumination setups. Our results show that a well-designed CSPH can consistently reduce data rates by 1–2 orders of magnitude without compromising depth precision.
{"title":"Compressive Single-Photon 3D Cameras","authors":"Felipe Gutierrez-Barragan, A. Ingle, T. Seets, Mohit Gupta, A. Velten","doi":"10.1109/CVPR52688.2022.01733","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.01733","url":null,"abstract":"Single-photon avalanche diodes (SPADs) are an emerging pixel technology for time-of-flight (ToF) 3D cameras that can capture the time-of-arrival of individual photons at picosecond resolution. To estimate depths, current SPAD-based 3D cameras measure the round-trip time of a laser pulse by building a per-pixel histogram of photon times-tamps. As the spatial and timestamp resolution of SPAD-based cameras increase, their output data rates far exceed the capacity of existing data transfer technologies. One major reason for SPAD's bandwidth-intensive operation is the tight coupling that exists between depth resolution and histogram resolution. To weaken this coupling, we propose compressive single-photon histograms (CSPH). CSPHs are a per-pixel compressive representation of the high-resolution histogram, that is built on-the-fly, as each photon is detected. They are based on a family of linear coding schemes that can be expressed as a simple matrix operation. We design different CSPH coding schemes for 3D imaging and evaluate them under different signal and background levels, laser waveforms, and illumination setups. Our results show that a well-designed CSPH can consistently reduce data rates by 1–2 orders of magnitude without compromising depth precision.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128473822","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 : 2022-06-01DOI: 10.1109/CVPR52688.2022.00174
Georgia Gkioxari, Nikhila Ravi, Justin Johnson
A 3D scene consists of a set of objects, each with a shape and a layout giving their position in space. Understanding 3D scenes from 2D images is an important goal, with ap-plications in robotics and graphics. While there have been recent advances in predicting 3D shape and layout from a single image, most approaches rely on 3D ground truth for training which is expensive to collect at scale. We overcome these limitations and propose a method that learns to predict 3D shape and layout for objects without any ground truth shape or layout information: instead we rely on multi-view images with 2D supervision which can more easily be col-lected at scale. Through extensive experiments on ShapeNet, Hypersim, and ScanNet we demonstrate that our approach scales to large datasets of realistic images, and compares favorably to methods relying on 3D ground truth. On Hy-persim and ScanNet where reliable 3D ground truth is not available, our approach outperforms supervised approaches trained on smaller and less diverse datasets.11Project page https://gkioxari.github.io/usl/
{"title":"Learning 3D Object Shape and Layout without 3D Supervision","authors":"Georgia Gkioxari, Nikhila Ravi, Justin Johnson","doi":"10.1109/CVPR52688.2022.00174","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.00174","url":null,"abstract":"A 3D scene consists of a set of objects, each with a shape and a layout giving their position in space. Understanding 3D scenes from 2D images is an important goal, with ap-plications in robotics and graphics. While there have been recent advances in predicting 3D shape and layout from a single image, most approaches rely on 3D ground truth for training which is expensive to collect at scale. We overcome these limitations and propose a method that learns to predict 3D shape and layout for objects without any ground truth shape or layout information: instead we rely on multi-view images with 2D supervision which can more easily be col-lected at scale. Through extensive experiments on ShapeNet, Hypersim, and ScanNet we demonstrate that our approach scales to large datasets of realistic images, and compares favorably to methods relying on 3D ground truth. On Hy-persim and ScanNet where reliable 3D ground truth is not available, our approach outperforms supervised approaches trained on smaller and less diverse datasets.11Project page https://gkioxari.github.io/usl/","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128806186","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 : 2022-06-01DOI: 10.1109/CVPR52688.2022.01210
Longguang Wang, Xiaoyu Dong, Yingqian Wang, Li Liu, Wei An, Y. Guo
Neural network quantization aims at reducing bit-widths of weights and activations for memory and computational efficiency. Since a linear quantizer (i.e., round(·) function) cannot well fit the bell-shaped distributions of weights and activations, many existing methods use predefined functions (e.g., exponential function) with learnable parameters to build the quantizer for joint optimization. However, these complicated quantizers introduce considerable computational overhead during inference since activation quantization should be conducted online. In this paper, we formulate the quantization process as a simple lookup operation and propose to learn lookup tables as quantizers. Specifically, we develop differentiable lookup tables and introduce several training strategies for optimization. Our lookup tables can be trained with the network in an end-to-end manner to fit the distributions in different layers and have very small additional computational cost. Comparison with previous methods show that quantized networks using our lookup tables achieve state-of-the-art performance on image classification, image super-resolution, and point cloud classification tasks.
{"title":"Learnable Lookup Table for Neural Network Quantization","authors":"Longguang Wang, Xiaoyu Dong, Yingqian Wang, Li Liu, Wei An, Y. Guo","doi":"10.1109/CVPR52688.2022.01210","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.01210","url":null,"abstract":"Neural network quantization aims at reducing bit-widths of weights and activations for memory and computational efficiency. Since a linear quantizer (i.e., round(·) function) cannot well fit the bell-shaped distributions of weights and activations, many existing methods use predefined functions (e.g., exponential function) with learnable parameters to build the quantizer for joint optimization. However, these complicated quantizers introduce considerable computational overhead during inference since activation quantization should be conducted online. In this paper, we formulate the quantization process as a simple lookup operation and propose to learn lookup tables as quantizers. Specifically, we develop differentiable lookup tables and introduce several training strategies for optimization. Our lookup tables can be trained with the network in an end-to-end manner to fit the distributions in different layers and have very small additional computational cost. Comparison with previous methods show that quantized networks using our lookup tables achieve state-of-the-art performance on image classification, image super-resolution, and point cloud classification tasks.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129264968","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 : 2022-06-01DOI: 10.1109/CVPR52688.2022.01976
Salvador Medina Maza, Denis Tomè, Carsten Stoll, M. Tiede, K. Munhall, A. Hauptmann, Iain Matthews
Advances in speech driven animation techniques allow the creation of convincing animations for virtual characters solely from audio data. Many existing approaches focus on facial and lip motion and they often do not provide realistic animation of the inner mouth. This paper addresses the problem of speech-driven inner mouth animation. Obtaining performance capture data of the tongue and jaw from video alone is difficult because the inner mouth is only partially observable during speech. In this work, we introduce a large-scale speech and mocap dataset that focuses on capturing tongue, jaw, and lip motion. This dataset enables research using data-driven techniques to generate realistic inner mouth animation from speech. We then propose a deep-learning based method for accurate and generalizable speech to tongue and jaw animation, and evaluate several encoder-decoder network architectures and audio feature encoders. We find that recent self-supervised deep learning based audio feature encoders are robust, generalize well to unseen speakers and content, and work best for our task. To demonstrate the practical application of our approach, we show animations on high-quality parametric 3D face models driven by the landmarks generated from our speech-to-tongue animation method.
{"title":"Speech Driven Tongue Animation","authors":"Salvador Medina Maza, Denis Tomè, Carsten Stoll, M. Tiede, K. Munhall, A. Hauptmann, Iain Matthews","doi":"10.1109/CVPR52688.2022.01976","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.01976","url":null,"abstract":"Advances in speech driven animation techniques allow the creation of convincing animations for virtual characters solely from audio data. Many existing approaches focus on facial and lip motion and they often do not provide realistic animation of the inner mouth. This paper addresses the problem of speech-driven inner mouth animation. Obtaining performance capture data of the tongue and jaw from video alone is difficult because the inner mouth is only partially observable during speech. In this work, we introduce a large-scale speech and mocap dataset that focuses on capturing tongue, jaw, and lip motion. This dataset enables research using data-driven techniques to generate realistic inner mouth animation from speech. We then propose a deep-learning based method for accurate and generalizable speech to tongue and jaw animation, and evaluate several encoder-decoder network architectures and audio feature encoders. We find that recent self-supervised deep learning based audio feature encoders are robust, generalize well to unseen speakers and content, and work best for our task. To demonstrate the practical application of our approach, we show animations on high-quality parametric 3D face models driven by the landmarks generated from our speech-to-tongue animation method.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129688855","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 : 2022-06-01DOI: 10.1109/CVPR52688.2022.01137
Huisi Wu, Zhaoze Wang, Youyi Song, L. Yang, Jing Qin
We study the semi-supervised learning problem, using a few labeled data and a large amount of unlabeled data to train the network, by developing a cross-patch dense contrastive learning framework, to segment cellular nuclei in histopathologic images. This task is motivated by the expensive burden on collecting labeled data for histopathologic image segmentation tasks. The key idea of our method is to align features of teacher and student networks, sampled from cross-image in both patch- and pixel-levels, for enforcing the intra-class compactness and inter-class separability of features that as we shown is helpful for extracting valuable knowledge from unlabeled data. We also design a novel optimization framework that combines consistency regularization and entropy minimization techniques, showing good property in eviction of gradient vanishing. We assess the proposed method on two publicly available datasets, and obtain positive results on extensive experiments, outperforming the state-of-the-art methods. Codes are available at https://github.com/zzw-szu/CDCL.
{"title":"Cross-patch Dense Contrastive Learning for Semi-supervised Segmentation of Cellular Nuclei in Histopathologic Images","authors":"Huisi Wu, Zhaoze Wang, Youyi Song, L. Yang, Jing Qin","doi":"10.1109/CVPR52688.2022.01137","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.01137","url":null,"abstract":"We study the semi-supervised learning problem, using a few labeled data and a large amount of unlabeled data to train the network, by developing a cross-patch dense contrastive learning framework, to segment cellular nuclei in histopathologic images. This task is motivated by the expensive burden on collecting labeled data for histopathologic image segmentation tasks. The key idea of our method is to align features of teacher and student networks, sampled from cross-image in both patch- and pixel-levels, for enforcing the intra-class compactness and inter-class separability of features that as we shown is helpful for extracting valuable knowledge from unlabeled data. We also design a novel optimization framework that combines consistency regularization and entropy minimization techniques, showing good property in eviction of gradient vanishing. We assess the proposed method on two publicly available datasets, and obtain positive results on extensive experiments, outperforming the state-of-the-art methods. Codes are available at https://github.com/zzw-szu/CDCL.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130299936","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 : 2022-06-01DOI: 10.1109/CVPR52688.2022.00073
Rongzhen Zhao, Jian Li, Zhenzhi Wu
In the biological visual pathway especially the retina, neurons are tiled along spatial dimensions with the electrical coupling as their local association, while in a convolution layer, kernels are placed along the channel dimension singly. We propose convolution of convolution, associating kernels in a layer and letting them collaborate spatially. With this method, a layer can provide feature maps with extra transformations and learn its kernels together instead of isolatedly. It is only used during training, bringing in negligible extra costs; then it can be re-parameterized to common convolution before testing, boosting performance gratuitously in tasks like classification, detection and segmentation. Our method works even better when larger receptive fields are demanded. The code is available on site: https://github.com/Genera1Z/ConvolutionOfConvolution.
{"title":"Convolution of Convolution: Let Kernels Spatially Collaborate","authors":"Rongzhen Zhao, Jian Li, Zhenzhi Wu","doi":"10.1109/CVPR52688.2022.00073","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.00073","url":null,"abstract":"In the biological visual pathway especially the retina, neurons are tiled along spatial dimensions with the electrical coupling as their local association, while in a convolution layer, kernels are placed along the channel dimension singly. We propose convolution of convolution, associating kernels in a layer and letting them collaborate spatially. With this method, a layer can provide feature maps with extra transformations and learn its kernels together instead of isolatedly. It is only used during training, bringing in negligible extra costs; then it can be re-parameterized to common convolution before testing, boosting performance gratuitously in tasks like classification, detection and segmentation. Our method works even better when larger receptive fields are demanded. The code is available on site: https://github.com/Genera1Z/ConvolutionOfConvolution.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130486626","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：