Pub Date : 2022-06-01DOI: 10.1109/CVPR52688.2022.00163
Andra Petrovai, S. Nedevschi
We present a novel self-distillation based self-supervised monocular depth estimation (SD-SSMDE) learning framework. In the first step, our network is trained in a self-supervised regime on high-resolution images with the photometric loss. The network is further used to generate pseudo depth labels for all the images in the training set. To improve the performance of our estimates, in the second step, we re-train the network with the scale invariant logarithmic loss supervised by pseudo labels. We resolve scale ambiguity and inter-frame scale consistency by introducing an automatically computed scale in our depth labels. To filter out noisy depth values, we devise a filtering scheme based on the 3D consistency between consecutive views. Extensive experiments demonstrate that each proposed component and the self-supervised learning framework improve the quality of the depth estimation over the baseline and achieve state-of-the-art results on the KITTI and Cityscapes datasets.
{"title":"Exploiting Pseudo Labels in a Self-Supervised Learning Framework for Improved Monocular Depth Estimation","authors":"Andra Petrovai, S. Nedevschi","doi":"10.1109/CVPR52688.2022.00163","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.00163","url":null,"abstract":"We present a novel self-distillation based self-supervised monocular depth estimation (SD-SSMDE) learning framework. In the first step, our network is trained in a self-supervised regime on high-resolution images with the photometric loss. The network is further used to generate pseudo depth labels for all the images in the training set. To improve the performance of our estimates, in the second step, we re-train the network with the scale invariant logarithmic loss supervised by pseudo labels. We resolve scale ambiguity and inter-frame scale consistency by introducing an automatically computed scale in our depth labels. To filter out noisy depth values, we devise a filtering scheme based on the 3D consistency between consecutive views. Extensive experiments demonstrate that each proposed component and the self-supervised learning framework improve the quality of the depth estimation over the baseline and achieve state-of-the-art results on the KITTI and Cityscapes datasets.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"244 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":"123918077","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/CVPR52688.2022.01597
Daigang Cai, Lichen Zhao, Jing Zhang, Lu Sheng, Dong Xu
Observing that the 3D captioning task and the 3D grounding task contain both shared and complementary information in nature, in this work, we propose a unified framework to jointly solve these two distinct but closely related tasks in a synergistic fashion, which consists of both shared task-agnostic modules and lightweight task-specific modules. On one hand, the shared task-agnostic modules aim to learn precise locations of objects, fine-grained attribute features to characterize different objects, and complex relations between objects, which benefit both captioning and visual grounding. On the other hand, by casting each of the two tasks as the proxy task of another one, the lightweight task-specific modules solve the captioning task and the grounding task respectively. Extensive experiments and ablation study on three 3D vision and language datasets demonstrate that our joint training frame-work achieves significant performance gains for each individual task and finally improves the state-of-the-art performance for both captioning and grounding tasks.
{"title":"3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds","authors":"Daigang Cai, Lichen Zhao, Jing Zhang, Lu Sheng, Dong Xu","doi":"10.1109/CVPR52688.2022.01597","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.01597","url":null,"abstract":"Observing that the 3D captioning task and the 3D grounding task contain both shared and complementary information in nature, in this work, we propose a unified framework to jointly solve these two distinct but closely related tasks in a synergistic fashion, which consists of both shared task-agnostic modules and lightweight task-specific modules. On one hand, the shared task-agnostic modules aim to learn precise locations of objects, fine-grained attribute features to characterize different objects, and complex relations between objects, which benefit both captioning and visual grounding. On the other hand, by casting each of the two tasks as the proxy task of another one, the lightweight task-specific modules solve the captioning task and the grounding task respectively. Extensive experiments and ablation study on three 3D vision and language datasets demonstrate that our joint training frame-work achieves significant performance gains for each individual task and finally improves the state-of-the-art performance for both captioning and grounding 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":"125768418","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/CVPR52688.2022.00646
Xinshuo Weng, B. Ivanovic, Kris Kitani, M. Pavone
Multi-agent trajectory prediction is critical for planning and decision-making in human-interactive autonomous systems, such as self-driving cars. However, most prediction models are developed separately from their upstream perception (detection and tracking) modules, assuming ground truth past trajectories as inputs. As a result, their performance degrades significantly when using real-world noisy tracking results as inputs. This is typically caused by the propagation of errors from tracking to prediction, such as noisy tracks, fragments and identity switches. To alleviate this propagation of errors, we propose a new prediction paradigm that uses detections and their affinity matrices across frames as inputs, removing the need for error- prone data association during tracking. Since affinity matrices contain “soft” information about the similarity and identity of detections across frames, making prediction directly from affinity matrices retains strictly more information than making prediction from the tracklets generated by data association. Experiments on large-scale, real-world autonomous driving datasets show that our affinity-based prediction scheme 11Our project website is at https://www.xinshuoweng.com/projects/Affinipred. reduces overall prediction errors by up to 57.9%, in comparison to standard prediction pipelines that use tracklets as inputs, with even more significant error reduction (up to 88.6%) if restricting the evaluation to challenging scenarios with tracking errors.
{"title":"Whose Track Is It Anyway? Improving Robustness to Tracking Errors with Affinity-based Trajectory Prediction","authors":"Xinshuo Weng, B. Ivanovic, Kris Kitani, M. Pavone","doi":"10.1109/CVPR52688.2022.00646","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.00646","url":null,"abstract":"Multi-agent trajectory prediction is critical for planning and decision-making in human-interactive autonomous systems, such as self-driving cars. However, most prediction models are developed separately from their upstream perception (detection and tracking) modules, assuming ground truth past trajectories as inputs. As a result, their performance degrades significantly when using real-world noisy tracking results as inputs. This is typically caused by the propagation of errors from tracking to prediction, such as noisy tracks, fragments and identity switches. To alleviate this propagation of errors, we propose a new prediction paradigm that uses detections and their affinity matrices across frames as inputs, removing the need for error- prone data association during tracking. Since affinity matrices contain “soft” information about the similarity and identity of detections across frames, making prediction directly from affinity matrices retains strictly more information than making prediction from the tracklets generated by data association. Experiments on large-scale, real-world autonomous driving datasets show that our affinity-based prediction scheme 11Our project website is at https://www.xinshuoweng.com/projects/Affinipred. reduces overall prediction errors by up to 57.9%, in comparison to standard prediction pipelines that use tracklets as inputs, with even more significant error reduction (up to 88.6%) if restricting the evaluation to challenging scenarios with tracking errors.","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":"125893902","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/CVPR52688.2022.00782
Zhenyi Wang, Li Shen, Tiehang Duan, Donglin Zhan, Le Fang, Mingchen Gao
Catastrophic forgetting (CF) frequently occurs when learning with non-stationary data distribution. The CF issue remains nearly unexplored and is more challenging when meta-learning on a sequence of domains (datasets), called sequential domain meta-learning (SDML). In this work, we propose a simple yet effective learning to learn approach, i.e., meta optimizer, to mitigate the CF problem in SDML. We first apply the proposed meta optimizer to the simplified setting of SDML, domain-aware meta-learning, where the domain labels and boundaries are known during the learning process. We propose dynamically freezing the network and incorporating it with the proposed meta optimizer by considering the domain nature during meta training. In addition, we extend the meta optimizer to the more general setting of SDML, domain-agnostic meta-learning, where domain labels and boundaries are unknown during the learning process. We propose a domain shift detection technique to capture latent domain change and equip the meta optimizer with it to work in this setting. The proposed meta optimizer is versatile and can be easily integrated with several existing meta-learning algorithms. Finally, we construct a challenging and large-scale benchmark consisting of 10 heterogeneous domains with a super long task sequence consisting of 100K tasks. We perform extensive experiments on the proposed benchmark for both settings and demonstrate the effectiveness of our proposed method, outperforming current strong baselines by a large margin.
{"title":"Learning to Learn and Remember Super Long Multi-Domain Task Sequence","authors":"Zhenyi Wang, Li Shen, Tiehang Duan, Donglin Zhan, Le Fang, Mingchen Gao","doi":"10.1109/CVPR52688.2022.00782","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.00782","url":null,"abstract":"Catastrophic forgetting (CF) frequently occurs when learning with non-stationary data distribution. The CF issue remains nearly unexplored and is more challenging when meta-learning on a sequence of domains (datasets), called sequential domain meta-learning (SDML). In this work, we propose a simple yet effective learning to learn approach, i.e., meta optimizer, to mitigate the CF problem in SDML. We first apply the proposed meta optimizer to the simplified setting of SDML, domain-aware meta-learning, where the domain labels and boundaries are known during the learning process. We propose dynamically freezing the network and incorporating it with the proposed meta optimizer by considering the domain nature during meta training. In addition, we extend the meta optimizer to the more general setting of SDML, domain-agnostic meta-learning, where domain labels and boundaries are unknown during the learning process. We propose a domain shift detection technique to capture latent domain change and equip the meta optimizer with it to work in this setting. The proposed meta optimizer is versatile and can be easily integrated with several existing meta-learning algorithms. Finally, we construct a challenging and large-scale benchmark consisting of 10 heterogeneous domains with a super long task sequence consisting of 100K tasks. We perform extensive experiments on the proposed benchmark for both settings and demonstrate the effectiveness of our proposed method, outperforming current strong baselines by a large margin.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"23 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":"129393847","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/CVPR52688.2022.00284
Rui Zhu, Zhengqin Li, J. Matai, F. Porikli, Manmohan Chandraker
Indoor scenes exhibit significant appearance variations due to myriad interactions between arbitrarily diverse object shapes, spatially-changing materials, and complex lighting. Shadows, highlights, and inter-reflections caused by visible and invisible light sources require reasoning about long-range interactions for inverse rendering, which seeks to recover the components of image formation, namely, shape, material, and lighting. In this work, our intuition is that the long-range attention learned by transformer architectures is ideally suited to solve longstanding challenges in single-image inverse rendering. We demonstrate with a specific instantiation of a dense vision transformer, IRISformer, that excels at both single-task and multi-task reasoning required for inverse rendering. Specifically, we propose a transformer architecture to simultaneously estimate depths, normals, spatially-varying albedo, roughness and lighting from a single image of an indoor scene. Our extensive evaluations on benchmark datasets demonstrate state-of-the-art results on each of the above tasks, enabling applications like object insertion and material editing in a single unconstrained real image, with greater photorealism than prior works. Code and data are publicly released.11https://github.com/ViLab-UCSD/IRISformer
{"title":"IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes","authors":"Rui Zhu, Zhengqin Li, J. Matai, F. Porikli, Manmohan Chandraker","doi":"10.1109/CVPR52688.2022.00284","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.00284","url":null,"abstract":"Indoor scenes exhibit significant appearance variations due to myriad interactions between arbitrarily diverse object shapes, spatially-changing materials, and complex lighting. Shadows, highlights, and inter-reflections caused by visible and invisible light sources require reasoning about long-range interactions for inverse rendering, which seeks to recover the components of image formation, namely, shape, material, and lighting. In this work, our intuition is that the long-range attention learned by transformer architectures is ideally suited to solve longstanding challenges in single-image inverse rendering. We demonstrate with a specific instantiation of a dense vision transformer, IRISformer, that excels at both single-task and multi-task reasoning required for inverse rendering. Specifically, we propose a transformer architecture to simultaneously estimate depths, normals, spatially-varying albedo, roughness and lighting from a single image of an indoor scene. Our extensive evaluations on benchmark datasets demonstrate state-of-the-art results on each of the above tasks, enabling applications like object insertion and material editing in a single unconstrained real image, with greater photorealism than prior works. Code and data are publicly released.11https://github.com/ViLab-UCSD/IRISformer","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"43 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":"128499694","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/CVPR52688.2022.01194
Jian Meng, Li Yang, Jinwoo Shin, Deliang Fan, J.-s. Seo
Contrastive learning (or its variants) has recently become a promising direction in the self-supervised learning domain, achieving similar performance as supervised learning with minimum fine-tuning. Despite the labeling efficiency, wide and large networks are required to achieve high accuracy, which incurs a high amount of computation and hinders the pragmatic merit of self-supervised learning. To effectively reduce the computation of insignificant features or channels, recent dynamic pruning algorithms for supervised learning employed auxiliary salience predictors. However, we found that such salience predictors cannot be easily trained when they are naïvely applied to contrastive learning from scratch. To address this issue, we propose contrastive dual gating (CDG), a novel dynamic pruning algorithm that skips the uninformative features during contrastive learning without hurting the trainability of the networks. We demonstrate the superiority of CDG with ResNet models for CIFAR-10, CIFAR-100, and ImageNet-100 datasets. Compared to our implementations of state-of-the-art dynamic pruning algorithms for self-supervised learning, CDG achieves up to 15% accuracy improvement for CIFAR-10 dataset with higher computation reduction.
{"title":"Contrastive Dual Gating: Learning Sparse Features With Contrastive Learning","authors":"Jian Meng, Li Yang, Jinwoo Shin, Deliang Fan, J.-s. Seo","doi":"10.1109/CVPR52688.2022.01194","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.01194","url":null,"abstract":"Contrastive learning (or its variants) has recently become a promising direction in the self-supervised learning domain, achieving similar performance as supervised learning with minimum fine-tuning. Despite the labeling efficiency, wide and large networks are required to achieve high accuracy, which incurs a high amount of computation and hinders the pragmatic merit of self-supervised learning. To effectively reduce the computation of insignificant features or channels, recent dynamic pruning algorithms for supervised learning employed auxiliary salience predictors. However, we found that such salience predictors cannot be easily trained when they are naïvely applied to contrastive learning from scratch. To address this issue, we propose contrastive dual gating (CDG), a novel dynamic pruning algorithm that skips the uninformative features during contrastive learning without hurting the trainability of the networks. We demonstrate the superiority of CDG with ResNet models for CIFAR-10, CIFAR-100, and ImageNet-100 datasets. Compared to our implementations of state-of-the-art dynamic pruning algorithms for self-supervised learning, CDG achieves up to 15% accuracy improvement for CIFAR-10 dataset with higher computation reduction.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"65 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":"128295360","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/CVPR52688.2022.00860
Jiqing Zhang, B. Dong, Haiwei Zhang, Jianchuan Ding, Felix Heide, Baocai Yin, Xin Yang
Event-based cameras bring a unique capability to tracking, being able to function in challenging real-world conditions as a direct result of their high temporal resolution and high dynamic range. These imagers capture events asynchronously that encode rich temporal and spatial information. However, effectively extracting this information from events remains an open challenge. In this work, we propose a spiking transformer network, STNet, for single object tracking. STNet dynamically extracts and fuses information from both temporal and spatial domains. In particular, the proposed architecture features a transformer module to provide global spatial information and a spiking neural network (SNN) module for extracting temporal cues. The spiking threshold of the SNN module is dynamically adjusted based on the statistical cues of the spatial information, which we find essential in providing robust SNN features. We fuse both feature branches dynamically with a novel cross-domain attention fusion algorithm. Extensive experiments on three event-based datasets, FE240hz, EED and VisEvent validate that the proposed STNet outperforms existing state-of-the-art methods in both tracking accuracy and speed with a significant margin. The code and pretrained models are at https://github.com/Jee-King/CVPR2022_STNet.
{"title":"Spiking Transformers for Event-based Single Object Tracking","authors":"Jiqing Zhang, B. Dong, Haiwei Zhang, Jianchuan Ding, Felix Heide, Baocai Yin, Xin Yang","doi":"10.1109/CVPR52688.2022.00860","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.00860","url":null,"abstract":"Event-based cameras bring a unique capability to tracking, being able to function in challenging real-world conditions as a direct result of their high temporal resolution and high dynamic range. These imagers capture events asynchronously that encode rich temporal and spatial information. However, effectively extracting this information from events remains an open challenge. In this work, we propose a spiking transformer network, STNet, for single object tracking. STNet dynamically extracts and fuses information from both temporal and spatial domains. In particular, the proposed architecture features a transformer module to provide global spatial information and a spiking neural network (SNN) module for extracting temporal cues. The spiking threshold of the SNN module is dynamically adjusted based on the statistical cues of the spatial information, which we find essential in providing robust SNN features. We fuse both feature branches dynamically with a novel cross-domain attention fusion algorithm. Extensive experiments on three event-based datasets, FE240hz, EED and VisEvent validate that the proposed STNet outperforms existing state-of-the-art methods in both tracking accuracy and speed with a significant margin. The code and pretrained models are at https://github.com/Jee-King/CVPR2022_STNet.","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":"127134995","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}
Despite the substantial progress of deep models for crack recognition, due to the inconsistent cracks in varying sizes, shapes, and noisy background textures, there still lacks the discriminative power of the deeply learned features when supervised by the cross-entropy loss. In this paper, we propose the geometry-aware guided loss (GAGL) that enhances the discrimination ability and is only applied in the training stage without extra computation and memory during inference. The GAGL consists of the feature-based geometry-aware projected gradient descent method (FGA-PGD) that approximates the geometric distances of the features to the class boundaries, and the geometry-aware update rule that learns an anchor of each class as the approximation of the feature expected to have the largest geometric distance to the corresponding class boundary. Then the discriminative power can be enhanced by minimizing the distances between the features and their corresponding class anchors in the feature space. To address the limited availability of related benchmarks, we collect a fully annotated dataset, namely, NPP2021, which involves inconsistent cracks and noisy backgrounds in real-world nuclear power plants. Our proposed GAGL outperforms the state of the arts on various benchmark datasets including CRACK2019, SDNET2018, and our NPP2021.
{"title":"Geometry-Aware Guided Loss for Deep Crack Recognition","authors":"Zhuangzhuang Chen, Jin Zhang, Zhuo-Jin Lai, Jie-Min Chen, Zun Liu, Jianqiang","doi":"10.1109/CVPR52688.2022.00466","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.00466","url":null,"abstract":"Despite the substantial progress of deep models for crack recognition, due to the inconsistent cracks in varying sizes, shapes, and noisy background textures, there still lacks the discriminative power of the deeply learned features when supervised by the cross-entropy loss. In this paper, we propose the geometry-aware guided loss (GAGL) that enhances the discrimination ability and is only applied in the training stage without extra computation and memory during inference. The GAGL consists of the feature-based geometry-aware projected gradient descent method (FGA-PGD) that approximates the geometric distances of the features to the class boundaries, and the geometry-aware update rule that learns an anchor of each class as the approximation of the feature expected to have the largest geometric distance to the corresponding class boundary. Then the discriminative power can be enhanced by minimizing the distances between the features and their corresponding class anchors in the feature space. To address the limited availability of related benchmarks, we collect a fully annotated dataset, namely, NPP2021, which involves inconsistent cracks and noisy backgrounds in real-world nuclear power plants. Our proposed GAGL outperforms the state of the arts on various benchmark datasets including CRACK2019, SDNET2018, and our NPP2021.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"24 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":"127189559","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/CVPR52688.2022.01830
Lin Li, Long Chen, Yifeng Huang, Zhimeng Zhang, Songyang Zhang, Jun Xiao
Unbiased SGG has achieved significant progress over recent years. However, almost all existing SGG models have overlooked the ground-truth annotation qualities of prevailing SGG datasets, i.e., they always assume: 1) all the manually annotated positive samples are equally correct; 2) all the un-annotated negative samples are absolutely background. In this paper, we argue that both assumptions are inapplicable to SGG: there are numerous “noisy” ground-truth predicate labels that break these two assumptions, and these noisy samples actually harm the training of unbiased SGG models. To this end, we propose a novel model-agnostic NoIsy label CorrEction strategy for SGG: NICE. NICE can not only detect noisy samples but also reassign more high-quality predicate labels to them. After the NICE training, we can obtain a cleaner version of SGG dataset for model training. Specifically, NICE consists of three components: negative Noisy Sample Detection (Neg-NSD), positive NSD (Pos-NSD), and Noisy Sample Correction (NSC). Firstly, in Neg-NSD, we formulate this task as an out-of-distribution detection problem, and assign pseudo labels to all detected noisy negative samples. Then, in Pos-NSD, we use a clustering-based algorithm to divide all positive samples into multiple sets, and treat the samples in the noisiest set as noisy positive samples. Lastly, in NSC, we use a simple but effective weighted KNN to reassign new predicate labels to noisy positive samples. Extensive results on different backbones and tasks have attested to the effectiveness and generalization abilities of each component of NICE.
{"title":"The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation","authors":"Lin Li, Long Chen, Yifeng Huang, Zhimeng Zhang, Songyang Zhang, Jun Xiao","doi":"10.1109/CVPR52688.2022.01830","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.01830","url":null,"abstract":"Unbiased SGG has achieved significant progress over recent years. However, almost all existing SGG models have overlooked the ground-truth annotation qualities of prevailing SGG datasets, i.e., they always assume: 1) all the manually annotated positive samples are equally correct; 2) all the un-annotated negative samples are absolutely background. In this paper, we argue that both assumptions are inapplicable to SGG: there are numerous “noisy” ground-truth predicate labels that break these two assumptions, and these noisy samples actually harm the training of unbiased SGG models. To this end, we propose a novel model-agnostic NoIsy label CorrEction strategy for SGG: NICE. NICE can not only detect noisy samples but also reassign more high-quality predicate labels to them. After the NICE training, we can obtain a cleaner version of SGG dataset for model training. Specifically, NICE consists of three components: negative Noisy Sample Detection (Neg-NSD), positive NSD (Pos-NSD), and Noisy Sample Correction (NSC). Firstly, in Neg-NSD, we formulate this task as an out-of-distribution detection problem, and assign pseudo labels to all detected noisy negative samples. Then, in Pos-NSD, we use a clustering-based algorithm to divide all positive samples into multiple sets, and treat the samples in the noisiest set as noisy positive samples. Lastly, in NSC, we use a simple but effective weighted KNN to reassign new predicate labels to noisy positive samples. Extensive results on different backbones and tasks have attested to the effectiveness and generalization abilities of each component of NICE.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"11 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":"127234422","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}
We present PlanarRecon - a novel framework for globally coherent detection and reconstruction of 3D planes from a posed monocular video. Unlike previous works that detect planes in 2D from a single image, PlanarRecon incrementally detects planes in 3D for each video fragment, which consists of a set of key frames, from a volumetric representation of the scene using neural networks. A learning-based tracking and fusion module is designed to merge planes from previous fragments to form a coherent global plane reconstruction. Such design allows Planar-Recon to integrate observations from multiple views within each fragment and temporal information across different ones, resulting in an accurate and coherent reconstruction of the scene abstraction with low-polygonal geometry. Experiments show that the proposed approach achieves state-of-the-art performances on the ScanNet dataset while being real-time. Code is available at the project page: https://neu-vi.github.io/planarrecon/.
{"title":"PlanarRecon: Realtime 3D Plane Detection and Reconstruction from Posed Monocular Videos","authors":"Yiming Xie, Matheus Gadelha, Fengting Yang, Xiaowei Zhou, Huaizu Jiang","doi":"10.1109/CVPR52688.2022.00612","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.00612","url":null,"abstract":"We present PlanarRecon - a novel framework for globally coherent detection and reconstruction of 3D planes from a posed monocular video. Unlike previous works that detect planes in 2D from a single image, PlanarRecon incrementally detects planes in 3D for each video fragment, which consists of a set of key frames, from a volumetric representation of the scene using neural networks. A learning-based tracking and fusion module is designed to merge planes from previous fragments to form a coherent global plane reconstruction. Such design allows Planar-Recon to integrate observations from multiple views within each fragment and temporal information across different ones, resulting in an accurate and coherent reconstruction of the scene abstraction with low-polygonal geometry. Experiments show that the proposed approach achieves state-of-the-art performances on the ScanNet dataset while being real-time. Code is available at the project page: https://neu-vi.github.io/planarrecon/.","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":"130036119","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：