Pub Date : 2021-10-01DOI: 10.1109/ICCV48922.2021.00777
Chaoning Zhang, Philipp Benz, Adil Karjauv, In-So Kweon
Universal adversarial perturbation (UAP), i.e. a single perturbation to fool the network for most images, is widely recognized as a more practical attack because the UAP can be generated beforehand and applied directly during the at-tack stage. One intriguing phenomenon regarding untargeted UAP is that most images are misclassified to a dominant label. This phenomenon has been reported in previous works while lacking a justified explanation, for which our work attempts to provide an alternative explanation. For a more practical universal attack, our investigation of untargeted UAP focuses on alleviating the dependence on the original training samples, from removing the need for sample labels to limiting the sample size. Towards strictly data-free untargeted UAP, our work proposes to exploit artificial Jigsaw images as the training samples, demonstrating competitive performance. We further investigate the possibility of exploiting the UAP for a data-free black-box attack which is arguably the most practical yet challenging threat model. We demonstrate that there exists optimization-free repetitive patterns which can successfully attack deep models. Code is available at https://bit.ly/3y0ZTIC.
{"title":"Data-free Universal Adversarial Perturbation and Black-box Attack","authors":"Chaoning Zhang, Philipp Benz, Adil Karjauv, In-So Kweon","doi":"10.1109/ICCV48922.2021.00777","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00777","url":null,"abstract":"Universal adversarial perturbation (UAP), i.e. a single perturbation to fool the network for most images, is widely recognized as a more practical attack because the UAP can be generated beforehand and applied directly during the at-tack stage. One intriguing phenomenon regarding untargeted UAP is that most images are misclassified to a dominant label. This phenomenon has been reported in previous works while lacking a justified explanation, for which our work attempts to provide an alternative explanation. For a more practical universal attack, our investigation of untargeted UAP focuses on alleviating the dependence on the original training samples, from removing the need for sample labels to limiting the sample size. Towards strictly data-free untargeted UAP, our work proposes to exploit artificial Jigsaw images as the training samples, demonstrating competitive performance. We further investigate the possibility of exploiting the UAP for a data-free black-box attack which is arguably the most practical yet challenging threat model. We demonstrate that there exists optimization-free repetitive patterns which can successfully attack deep models. Code is available at https://bit.ly/3y0ZTIC.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"1 1","pages":"7848-7857"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82303378","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}
In recent years, sparse voxel-based methods have be-come the state-of-the-arts for 3D semantic segmentation of indoor scenes, thanks to the powerful 3D CNNs. Nevertheless, being oblivious to the underlying geometry, voxel-based methods suffer from ambiguous features on spatially close objects and struggle with handling complex and irregular geometries due to the lack of geodesic information. In view of this, we present Voxel-Mesh Network (VMNet), a novel 3D deep architecture that operates on the voxel and mesh representations leveraging both the Euclidean and geodesic information. Intuitively, the Euclidean information extracted from voxels can offer contextual cues representing interactions between nearby objects, while the geodesic information extracted from meshes can help separate objects that are spatially close but have disconnected surfaces. To incorporate such information from the two domains, we design an intra-domain attentive module for effective feature aggregation and an inter-domain attentive module for adaptive feature fusion. Experimental results validate the effectiveness of VMNet: specifically, on the challenging ScanNet dataset for large-scale segmentation of indoor scenes, it outperforms the state-of-the-art SparseConvNet and MinkowskiNet (74.6% vs 72.5% and 73.6% in mIoU) with a simpler network structure (17M vs 30M and 38M parameters). Code release: https://github.com/hzykent/VMNet
{"title":"VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation","authors":"Zeyu Hu, Xuyang Bai, Jiaxiang Shang, Runze Zhang, Jiayu Dong, Xin Wang, Guangyuan Sun, Hongbo Fu, Chiew-Lan Tai","doi":"10.1109/ICCV48922.2021.01520","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.01520","url":null,"abstract":"In recent years, sparse voxel-based methods have be-come the state-of-the-arts for 3D semantic segmentation of indoor scenes, thanks to the powerful 3D CNNs. Nevertheless, being oblivious to the underlying geometry, voxel-based methods suffer from ambiguous features on spatially close objects and struggle with handling complex and irregular geometries due to the lack of geodesic information. In view of this, we present Voxel-Mesh Network (VMNet), a novel 3D deep architecture that operates on the voxel and mesh representations leveraging both the Euclidean and geodesic information. Intuitively, the Euclidean information extracted from voxels can offer contextual cues representing interactions between nearby objects, while the geodesic information extracted from meshes can help separate objects that are spatially close but have disconnected surfaces. To incorporate such information from the two domains, we design an intra-domain attentive module for effective feature aggregation and an inter-domain attentive module for adaptive feature fusion. Experimental results validate the effectiveness of VMNet: specifically, on the challenging ScanNet dataset for large-scale segmentation of indoor scenes, it outperforms the state-of-the-art SparseConvNet and MinkowskiNet (74.6% vs 72.5% and 73.6% in mIoU) with a simpler network structure (17M vs 30M and 38M parameters). Code release: https://github.com/hzykent/VMNet","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"3 1","pages":"15468-15478"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82466066","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 : 2021-10-01DOI: 10.1109/ICCV48922.2021.00255
Ziteng Cui, Guo-Jun Qi, Lin Gu, Shaodi You, Zenghui Zhang, T. Harada
Dark environment becomes a challenge for computer vision algorithms owing to insufficient photons and undesirable noise. To enhance object detection in a dark environment, we propose a novel multitask auto encoding transformation (MAET) model which is able to explore the intrinsic pattern behind illumination translation. In a self-supervision manner, the MAET learns the intrinsic visual structure by encoding and decoding the realistic illumination-degrading transformation considering the physical noise model and image signal processing (ISP). Based on this representation, we achieve the object detection task by decoding the bounding box coordinates and classes. To avoid the over-entanglement of two tasks, our MAET disentangles the object and degrading features by imposing an orthogonal tangent regularity. This forms a parametric manifold along which multitask predictions can be geometrically formulated by maximizing the orthogonality between the tangents along the outputs of respective tasks. Our framework can be implemented based on the mainstream object detection architecture and directly trained end-to-end using normal target detection datasets, such as VOC and COCO. We have achieved the state-of-the-art performance using synthetic and real-world datasets. Codes will be released at https://github.com/cuiziteng/MAET.
{"title":"Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection","authors":"Ziteng Cui, Guo-Jun Qi, Lin Gu, Shaodi You, Zenghui Zhang, T. Harada","doi":"10.1109/ICCV48922.2021.00255","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00255","url":null,"abstract":"Dark environment becomes a challenge for computer vision algorithms owing to insufficient photons and undesirable noise. To enhance object detection in a dark environment, we propose a novel multitask auto encoding transformation (MAET) model which is able to explore the intrinsic pattern behind illumination translation. In a self-supervision manner, the MAET learns the intrinsic visual structure by encoding and decoding the realistic illumination-degrading transformation considering the physical noise model and image signal processing (ISP). Based on this representation, we achieve the object detection task by decoding the bounding box coordinates and classes. To avoid the over-entanglement of two tasks, our MAET disentangles the object and degrading features by imposing an orthogonal tangent regularity. This forms a parametric manifold along which multitask predictions can be geometrically formulated by maximizing the orthogonality between the tangents along the outputs of respective tasks. Our framework can be implemented based on the mainstream object detection architecture and directly trained end-to-end using normal target detection datasets, such as VOC and COCO. We have achieved the state-of-the-art performance using synthetic and real-world datasets. Codes will be released at https://github.com/cuiziteng/MAET.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"18 1","pages":"2533-2542"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87106535","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}
Object detection aims to accurately locate and classify objects in an image, which requires precise object representations. Existing methods usually use rectangular anchor boxes or a set of points to represent objects. However, these methods either introduce background noise or miss the continuous appearance information inside the object, and thus cause incorrect detection results. In this paper, we propose a novel anchor-free object detection network, called Cross-Det, which uses a set of growing cross lines along horizontal and vertical axes as object representations. An object can be flexibly represented as cross lines in different combinations. It not only can effectively reduce the interference of noise, but also take into account the continuous object information, which is useful to enhance the discriminability of object features and find the object boundaries. Based on the learned cross lines, we propose a crossline extraction module to adaptively capture features of cross lines. Furthermore, we design a decoupled regression mechanism to regress the localization along the horizontal and vertical directions respectively, which helps to decrease the optimization difficulty because the optimization space is limited to a specific direction. Our method achieves consistently improvement on the PASCAL VOC and MS-COCO datasets. The experiment results demonstrate the effectiveness of our proposed method. Code can be available at: https://github.com/QiuHeqian/CrossDet.
{"title":"CrossDet: Crossline Representation for Object Detection","authors":"Heqian Qiu, Hongliang Li, Qingbo Wu, Jianhua Cui, Zichen Song, Lanxiao Wang, Minjian Zhang","doi":"10.1109/ICCV48922.2021.00318","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00318","url":null,"abstract":"Object detection aims to accurately locate and classify objects in an image, which requires precise object representations. Existing methods usually use rectangular anchor boxes or a set of points to represent objects. However, these methods either introduce background noise or miss the continuous appearance information inside the object, and thus cause incorrect detection results. In this paper, we propose a novel anchor-free object detection network, called Cross-Det, which uses a set of growing cross lines along horizontal and vertical axes as object representations. An object can be flexibly represented as cross lines in different combinations. It not only can effectively reduce the interference of noise, but also take into account the continuous object information, which is useful to enhance the discriminability of object features and find the object boundaries. Based on the learned cross lines, we propose a crossline extraction module to adaptively capture features of cross lines. Furthermore, we design a decoupled regression mechanism to regress the localization along the horizontal and vertical directions respectively, which helps to decrease the optimization difficulty because the optimization space is limited to a specific direction. Our method achieves consistently improvement on the PASCAL VOC and MS-COCO datasets. The experiment results demonstrate the effectiveness of our proposed method. Code can be available at: https://github.com/QiuHeqian/CrossDet.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"72 1","pages":"3175-3184"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86138290","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 : 2021-10-01DOI: 10.1109/ICCV48922.2021.00203
Junwen Chen, Yu Kong Golisano
Video entailment aims at determining if a hypothesis textual statement is entailed or contradicted by a premise video. The main challenge of video entailment is that it requires fine-grained reasoning to understand the complex and long story-based videos. To this end, we propose to incorporate visual grounding to the entailment by explicitly linking the entities described in the statement to the evidence in the video. If the entities are grounded in the video, we enhance the entailment judgment by focusing on the frames where the entities occur. Besides, in the entailment dataset, the entailed/contradictory (also named as real/fake) statements are formed in pairs with subtle discrepancy, which allows an add-on explanation module to predict which words or phrases make the statement contradictory to the video and regularize the training of the entailment judgment. Experimental results demonstrate that our approach outperforms the state-of-the-art methods.
{"title":"Explainable Video Entailment with Grounded Visual Evidence","authors":"Junwen Chen, Yu Kong Golisano","doi":"10.1109/ICCV48922.2021.00203","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00203","url":null,"abstract":"Video entailment aims at determining if a hypothesis textual statement is entailed or contradicted by a premise video. The main challenge of video entailment is that it requires fine-grained reasoning to understand the complex and long story-based videos. To this end, we propose to incorporate visual grounding to the entailment by explicitly linking the entities described in the statement to the evidence in the video. If the entities are grounded in the video, we enhance the entailment judgment by focusing on the frames where the entities occur. Besides, in the entailment dataset, the entailed/contradictory (also named as real/fake) statements are formed in pairs with subtle discrepancy, which allows an add-on explanation module to predict which words or phrases make the statement contradictory to the video and regularize the training of the entailment judgment. Experimental results demonstrate that our approach outperforms the state-of-the-art methods.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"23 1","pages":"2001-2010"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86294362","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 : 2021-10-01DOI: 10.1109/ICCV48922.2021.00759
Ahmed A. Abusnaina, Yuhang Wu, Sunpreet S. Arora, Yizhen Wang, Fei Wang, Hao Yang, David A. Mohaisen
Detection of adversarial examples with high accuracy is critical for the security of deployed deep neural network-based models. We present the first graph-based adversarial detection method that constructs a Latent Neighborhood Graph (LNG) around an input example to determine if the input example is adversarial. Given an input example, selected reference adversarial and benign examples (represented as LNG nodes in Figure 1) are used to capture the local manifold in the vicinity of the input example. The LNG node connectivity parameters are optimized jointly with the parameters of a graph attention network in an end-to-end manner to determine the optimal graph topology for adversarial example detection. The graph attention network is used to determine if the LNG is derived from an adversarial or benign input example. Experimental evaluations on CIFAR-10, STL-10, and ImageNet datasets, using six adversarial attack methods, demonstrate that the proposed method outperforms state-of-the-art adversarial detection methods in white-box and gray-box settings. The proposed method is able to successfully detect adversarial examples crafted with small perturbations using unseen attacks.
{"title":"Adversarial Example Detection Using Latent Neighborhood Graph","authors":"Ahmed A. Abusnaina, Yuhang Wu, Sunpreet S. Arora, Yizhen Wang, Fei Wang, Hao Yang, David A. Mohaisen","doi":"10.1109/ICCV48922.2021.00759","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00759","url":null,"abstract":"Detection of adversarial examples with high accuracy is critical for the security of deployed deep neural network-based models. We present the first graph-based adversarial detection method that constructs a Latent Neighborhood Graph (LNG) around an input example to determine if the input example is adversarial. Given an input example, selected reference adversarial and benign examples (represented as LNG nodes in Figure 1) are used to capture the local manifold in the vicinity of the input example. The LNG node connectivity parameters are optimized jointly with the parameters of a graph attention network in an end-to-end manner to determine the optimal graph topology for adversarial example detection. The graph attention network is used to determine if the LNG is derived from an adversarial or benign input example. Experimental evaluations on CIFAR-10, STL-10, and ImageNet datasets, using six adversarial attack methods, demonstrate that the proposed method outperforms state-of-the-art adversarial detection methods in white-box and gray-box settings. The proposed method is able to successfully detect adversarial examples crafted with small perturbations using unseen attacks.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"175 1","pages":"7667-7676"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86072823","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}
Event cameras are bio-inspired sensors that respond to brightness changes asynchronously and output in the form of event streams instead of frame-based images. They own outstanding advantages compared with traditional cameras: higher temporal resolution, higher dynamic range, and lower power consumption. However, the spatial resolution of existing event cameras is insufficient and challenging to be enhanced at the hardware level while maintaining the asynchronous philosophy of circuit design. Therefore, it is imperative to explore the algorithm of event stream super-resolution, which is a non-trivial task due to the sparsity and strong spatio-temporal correlation of the events from an event camera. In this paper, we propose an end-to-end framework based on spiking neural network for event stream super-resolution, which can generate high-resolution (HR) event stream from the input low-resolution (LR) event stream. A spatiotemporal constraint learning mechanism is proposed to learn the spatial and temporal distributions of the event stream simultaneously. We validate our method on four large-scale datasets and the results show that our method achieves state-of-the-art performance. The satisfying results on two downstream applications, i.e. object classification and image reconstruction, further demonstrate the usability of our method. To prove the application potential of our method, we deploy it on a mobile platform. The high-quality HR event stream generated by our real-time system demonstrates the effectiveness and efficiency of our method.
{"title":"Event Stream Super-Resolution via Spatiotemporal Constraint Learning","authors":"Siqi Li, Yutong Feng, Yipeng Li, Yu Jiang, C. Zou, Yue Gao","doi":"10.1109/ICCV48922.2021.00444","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00444","url":null,"abstract":"Event cameras are bio-inspired sensors that respond to brightness changes asynchronously and output in the form of event streams instead of frame-based images. They own outstanding advantages compared with traditional cameras: higher temporal resolution, higher dynamic range, and lower power consumption. However, the spatial resolution of existing event cameras is insufficient and challenging to be enhanced at the hardware level while maintaining the asynchronous philosophy of circuit design. Therefore, it is imperative to explore the algorithm of event stream super-resolution, which is a non-trivial task due to the sparsity and strong spatio-temporal correlation of the events from an event camera. In this paper, we propose an end-to-end framework based on spiking neural network for event stream super-resolution, which can generate high-resolution (HR) event stream from the input low-resolution (LR) event stream. A spatiotemporal constraint learning mechanism is proposed to learn the spatial and temporal distributions of the event stream simultaneously. We validate our method on four large-scale datasets and the results show that our method achieves state-of-the-art performance. The satisfying results on two downstream applications, i.e. object classification and image reconstruction, further demonstrate the usability of our method. To prove the application potential of our method, we deploy it on a mobile platform. The high-quality HR event stream generated by our real-time system demonstrates the effectiveness and efficiency of our method.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"49 1","pages":"4460-4469"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83673753","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 : 2021-10-01DOI: 10.1109/ICCV48922.2021.00328
Hanxue Liang, Chenhan Jiang, Dapeng Feng, Xin Chen, Hang Xu, Xiaodan Liang, Wei Zhang, Zhenguo Li, L. Gool, Sun Yat-sen
Current 3D object detection paradigms highly rely on extensive annotation efforts, which makes them not practical in many real-world industrial applications. Inspired by that a human driver can keep accumulating experiences from self-exploring the roads without any tutor’s guidance, we first step forwards to explore a simple yet effective self-supervised learning framework tailored for LiDAR-based 3D object detection. Although the self-supervised pipeline has achieved great success in 2D domain, the characteristic challenges (e.g., complex geometry structure and various 3D object views) encountered in the 3D domain hinder the direct adoption of existing techniques that often contrast the 2D augmented data or cluster single-view features. Here we present a novel self-supervised 3D Object detection framework that seamlessly integrates the geometry-aware contrast and clustering harmonization to lift the unsupervised 3D representation learning, named GCC-3D. First, GCC-3D introduces a Geometric-Aware Contrastive objective to learn spatial-sensitive local structure representation. This objective enforces the spatially close voxels to have high feature similarity. Second, a Pseudo-Instance Clustering harmonization mechanism is proposed to encourage that different views of pseudo-instances should have consistent similarities to clustering prototype centers. This module endows our model semantic discriminative capacity. Extensive experiments demonstrate our GCC-3D achieves significant performance improvement on data-efficient 3D object detection benchmarks (nuScenes and Waymo). Moreover, our GCC-3D framework can achieve state-of-the art performances on all popular 3D object detection benchmarks.
{"title":"Exploring Geometry-aware Contrast and Clustering Harmonization for Self-supervised 3D Object Detection","authors":"Hanxue Liang, Chenhan Jiang, Dapeng Feng, Xin Chen, Hang Xu, Xiaodan Liang, Wei Zhang, Zhenguo Li, L. Gool, Sun Yat-sen","doi":"10.1109/ICCV48922.2021.00328","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00328","url":null,"abstract":"Current 3D object detection paradigms highly rely on extensive annotation efforts, which makes them not practical in many real-world industrial applications. Inspired by that a human driver can keep accumulating experiences from self-exploring the roads without any tutor’s guidance, we first step forwards to explore a simple yet effective self-supervised learning framework tailored for LiDAR-based 3D object detection. Although the self-supervised pipeline has achieved great success in 2D domain, the characteristic challenges (e.g., complex geometry structure and various 3D object views) encountered in the 3D domain hinder the direct adoption of existing techniques that often contrast the 2D augmented data or cluster single-view features. Here we present a novel self-supervised 3D Object detection framework that seamlessly integrates the geometry-aware contrast and clustering harmonization to lift the unsupervised 3D representation learning, named GCC-3D. First, GCC-3D introduces a Geometric-Aware Contrastive objective to learn spatial-sensitive local structure representation. This objective enforces the spatially close voxels to have high feature similarity. Second, a Pseudo-Instance Clustering harmonization mechanism is proposed to encourage that different views of pseudo-instances should have consistent similarities to clustering prototype centers. This module endows our model semantic discriminative capacity. Extensive experiments demonstrate our GCC-3D achieves significant performance improvement on data-efficient 3D object detection benchmarks (nuScenes and Waymo). Moreover, our GCC-3D framework can achieve state-of-the art performances on all popular 3D object detection benchmarks.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"94 1","pages":"3273-3282"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83908346","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 : 2021-10-01DOI: 10.1109/ICCV48922.2021.01116
Baowen Zhang, Yangang Wang, Xiaoming Deng, Yinda Zhang, P. Tan, Cuixia Ma, Hongan Wang
In this paper, we propose a novel deep learning framework to reconstruct 3D hand poses and shapes of two interacting hands from a single color image. Previous methods designed for single hand cannot be easily applied for the two hand scenario because of the heavy inter-hand occlusion and larger solution space. In order to address the occlusion and similar appearance between hands that may confuse the network, we design a hand pose-aware attention module to extract features associated to each individual hand respectively. We then leverage the two hand context presented in interaction to propose a context-aware cascaded refinement that improves the hand pose and shape accuracy of each hand conditioned on the context between interacting hands. Extensive experiments on the main benchmark datasets demonstrate that our method predicts accurate 3D hand pose and shape from single color image, and achieves the state-of-the-art performance. Code is available in project webpage https://baowenz.github.io/Intershape/.
{"title":"Interacting Two-Hand 3D Pose and Shape Reconstruction from Single Color Image","authors":"Baowen Zhang, Yangang Wang, Xiaoming Deng, Yinda Zhang, P. Tan, Cuixia Ma, Hongan Wang","doi":"10.1109/ICCV48922.2021.01116","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.01116","url":null,"abstract":"In this paper, we propose a novel deep learning framework to reconstruct 3D hand poses and shapes of two interacting hands from a single color image. Previous methods designed for single hand cannot be easily applied for the two hand scenario because of the heavy inter-hand occlusion and larger solution space. In order to address the occlusion and similar appearance between hands that may confuse the network, we design a hand pose-aware attention module to extract features associated to each individual hand respectively. We then leverage the two hand context presented in interaction to propose a context-aware cascaded refinement that improves the hand pose and shape accuracy of each hand conditioned on the context between interacting hands. Extensive experiments on the main benchmark datasets demonstrate that our method predicts accurate 3D hand pose and shape from single color image, and achieves the state-of-the-art performance. Code is available in project webpage https://baowenz.github.io/Intershape/.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"71 1","pages":"11334-11343"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83936440","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 : 2021-10-01DOI: 10.1109/ICCV48922.2021.00195
Shijie Li, Yanying Zhou, Jinhui Yi, Juergen Gall
Trajectory forecasting is a crucial step for autonomous vehicles and mobile robots in order to navigate and interact safely. In order to handle the spatial interactions between objects, graph-based approaches have been proposed. These methods, however, model motion on a frame-to-frame basis and do not provide a strong temporal model. To overcome this limitation, we propose a compact model called Spatial-Temporal Consistency Network (STC-Net). In STC-Net, dilated temporal convolutions are introduced to model long-range dependencies along each trajectory for better temporal modeling while graph convolutions are employed to model the spatial interaction among different trajectories. Furthermore, we propose a feature-wise convolution to generate the predicted trajectories in one pass and refine the forecast trajectories together with the reconstructed observed trajectories. We demonstrate that STC-Net generates spatially and temporally consistent trajectories and outperforms other graph-based methods. Since STC-Net requires only 0.7k parameters and forecasts the future with a latency of only 1.3ms, it advances the state-of-the-art and satisfies the requirements for realistic applications.
{"title":"Spatial-Temporal Consistency Network for Low-Latency Trajectory Forecasting","authors":"Shijie Li, Yanying Zhou, Jinhui Yi, Juergen Gall","doi":"10.1109/ICCV48922.2021.00195","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00195","url":null,"abstract":"Trajectory forecasting is a crucial step for autonomous vehicles and mobile robots in order to navigate and interact safely. In order to handle the spatial interactions between objects, graph-based approaches have been proposed. These methods, however, model motion on a frame-to-frame basis and do not provide a strong temporal model. To overcome this limitation, we propose a compact model called Spatial-Temporal Consistency Network (STC-Net). In STC-Net, dilated temporal convolutions are introduced to model long-range dependencies along each trajectory for better temporal modeling while graph convolutions are employed to model the spatial interaction among different trajectories. Furthermore, we propose a feature-wise convolution to generate the predicted trajectories in one pass and refine the forecast trajectories together with the reconstructed observed trajectories. We demonstrate that STC-Net generates spatially and temporally consistent trajectories and outperforms other graph-based methods. Since STC-Net requires only 0.7k parameters and forecasts the future with a latency of only 1.3ms, it advances the state-of-the-art and satisfies the requirements for realistic applications.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"95 1","pages":"1920-1929"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83978362","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：