2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)最新文献_第3页

Exploring Joint Embedding Architectures and Data Augmentations for Self-Supervised Representation Learning in Event-Based Vision 探索基于事件视觉的自监督表示学习的联合嵌入架构和数据增强

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2023-06-01 DOI: 10.1109/CVPRW59228.2023.00405

Sami Barchid, José Mennesson, C. Djeraba

{"title":"Exploring Joint Embedding Architectures and Data Augmentations for Self-Supervised Representation Learning in Event-Based Vision","authors":"Sami Barchid, José Mennesson, C. Djeraba","doi":"10.1109/CVPRW59228.2023.00405","DOIUrl":"https://doi.org/10.1109/CVPRW59228.2023.00405","url":null,"abstract":"This paper proposes a self-supervised representation learning (SSRL) framework for event-based vision, which leverages various lightweight convolutional neural networks (CNNs) including 2D-, 3D-, and Spiking CNNs. The method uses a joint embedding architecture to maximize the agreement between features extracted from different views of the same event sequence. Popular event data augmentation techniques are employed to design an efficient augmentation policy for event-based SSRL, and we provide novel data augmentation methods to enhance the pretraining pipeline. Given the novelty of SSRL for event-based vision, we elaborate standard evaluation protocols and use them to evaluate our approach. Our study demonstrates that pretrained CNNs acquire effective and transferable features, enabling them to achieve competitive performance in object or action recognition across various commonly used event-based datasets, even in a low-data regime. This paper also conducts an experimental analysis of the extracted features regarding the Uniformity-Tolerance tradeoff to assess their quality, and measure the similarity of representations using linear Center Kernel Alignement. These quantitative measurements reinforce our observations from the performance benchmarks and show substantial differences between the learned representations of all types of CNNs despite being optimized with the same approach.","PeriodicalId":355438,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113966183","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}

引用次数: 2

RB-Dust - A Reference-based Dataset for Vision-based Dust Removal RB-Dust -基于参考的基于视觉的粉尘去除数据集

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2023-06-01 DOI: 10.1109/CVPRW59228.2023.00121

P. Buckel, T. Oksanen, Thomas Dietmueller

{"title":"RB-Dust - A Reference-based Dataset for Vision-based Dust Removal","authors":"P. Buckel, T. Oksanen, Thomas Dietmueller","doi":"10.1109/CVPRW59228.2023.00121","DOIUrl":"https://doi.org/10.1109/CVPRW59228.2023.00121","url":null,"abstract":"Dust in the agricultural landscape is a significant challenge and influences, for example, the environmental perception of autonomous agricultural machines. Image enhancement algorithms can be used to reduce dust. However, these require dusty and dust-free images of the same environment for validation. In fact, to date, there is no dataset that we are aware of that addresses this issue. Therefore, we present the agriscapes RB-Dust dataset, which is named after its purpose of reference-based dust removal. It is not possible to take pictures from the cabin during tillage, as this would cause shifts in the images. Because of this, we built a setup from which it is possible to take images from a stationary position close to the passing tractor. The test setup was based on a half-sided gate through which the tractor could drive. The field tests were carried out on a farm in Bavaria, Germany, during tillage. During the field tests, other parameters such as soil moisture and wind speed were controlled, as these significantly affect dust development. We validated our dataset with contrast enhancement and image dehazing algorithms and analyzed the generalizability from recordings from the moving tractor. Finally, we demonstrate the application of dust removal based on a high-level vision task, such as person classification. Our empirical study confirms the validity of RB-Dust for vision-based dust removal in agriculture.","PeriodicalId":355438,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126442226","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}

引用次数: 0

A Data-Driven Approach based on Dynamic Mode Decomposition for Efficient Encoding of Dynamic Light Fields 一种基于动态模式分解的数据驱动动态光场高效编码方法

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2023-06-01 DOI: 10.1109/CVPRW59228.2023.00347

Joshitha Ravishankar, Sally Khaidem, Mansi Sharma

{"title":"A Data-Driven Approach based on Dynamic Mode Decomposition for Efficient Encoding of Dynamic Light Fields","authors":"Joshitha Ravishankar, Sally Khaidem, Mansi Sharma","doi":"10.1109/CVPRW59228.2023.00347","DOIUrl":"https://doi.org/10.1109/CVPRW59228.2023.00347","url":null,"abstract":"Dynamic light fields provide a richer, more realistic 3D representation of a moving scene. However, this leads to higher data rates since excess storage and transmission requirements are needed. We propose a novel approach to efficiently represent and encode dynamic light field data for display applications based on dynamic mode decomposition (DMD). Acquired images are firstly obtained through optimized coded aperture patterns for each temporal frame/camera viewpoint of a dynamic light field. The underlying spatial, angular, and temporal correlations are effectively exploited by a data-driven DMD on these acquired images arranged as time snapshots. Next, High Efficiency Video Coding (HEVC) removes redundancies in light field data, including intra-frame and inter-frame redundancies, while maintaining high reconstruction quality. The proposed scheme is the first of its kind to treat light field videos as mathematical dynamical systems, leverage on dynamic modes of acquired images, and gain flexible coding at various bitrates. Experimental results demonstrate our scheme’s superior compression efficiency and bitrate savings compared to the direct encoding of acquired images using HEVC codec.","PeriodicalId":355438,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122249921","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}

引用次数: 0

LiDAR-Based Localization on Highways Using Raw Data and Pole-Like Object Features 基于激光雷达的高速公路原始数据和极状物体特征定位

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2023-06-01 DOI: 10.1109/CVPRW59228.2023.00028

Sheng-Cheng Lee, Victor Lu, Chieh-Chih Wang, Wen-Chieh Lin

{"title":"LiDAR-Based Localization on Highways Using Raw Data and Pole-Like Object Features","authors":"Sheng-Cheng Lee, Victor Lu, Chieh-Chih Wang, Wen-Chieh Lin","doi":"10.1109/CVPRW59228.2023.00028","DOIUrl":"https://doi.org/10.1109/CVPRW59228.2023.00028","url":null,"abstract":"Poles on highways provide important cues for how a scan should be localized onto a map. However existing point cloud scan matching algorithms do not fully leverage such cues, leading to suboptimal matching accuracy in highway environments. To improve the ability to match in such scenarios, we include pole-like objects for lateral information and add this information to the current matching algorithm. First, we classify the points from the LiDAR sensor using the Random Forests classifier to find the points that represent poles. Each detected pole point will then generate a residual by the distance to the nearest pole in map. The pole residuals are later optimized along with the point-to-distribution residuals proposed in the normal distributions transform (NDT) using a nonlinear least squares optimization to get the localization result. Compared to the baseline (NDT), our proposed method obtains a 34% improvement in accuracy on highway scenes in the localization problem. In addition, our experiment shows that the convergence area is significantly enlarged, increasing the usability of the self-driving car localization algorithm on highway scenarios.","PeriodicalId":355438,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"181 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128178324","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}

引用次数: 0

MoveEnet: Online High-Frequency Human Pose Estimation with an Event Camera MoveEnet:使用事件相机进行在线高频人体姿势估计

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2023-06-01 DOI: 10.1109/CVPRW59228.2023.00420

Gaurvi Goyal, Franco Di Pietro, N. Carissimi, Arren J. Glover, C. Bartolozzi

引用次数: 0

Underwater Moving Object Detection using an End-to-End Encoder-Decoder Architecture and GraphSage with Aggregator and Refactoring 基于端到端编码器-解码器结构和GraphSage的水下运动目标检测

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2023-06-01 DOI: 10.1109/CVPRW59228.2023.00597

Meghna Kapoor, Suvam Patra, B. Subudhi, V. Jakhetiya, Ankur Bansal

{"title":"Underwater Moving Object Detection using an End-to-End Encoder-Decoder Architecture and GraphSage with Aggregator and Refactoring","authors":"Meghna Kapoor, Suvam Patra, B. Subudhi, V. Jakhetiya, Ankur Bansal","doi":"10.1109/CVPRW59228.2023.00597","DOIUrl":"https://doi.org/10.1109/CVPRW59228.2023.00597","url":null,"abstract":"Underwater environments are greatly affected by several factors, including low visibility, high turbidity, backscattering, dynamic background, etc., and hence pose challenges in object detection. Several algorithms consider convolutional neural networks to extract deep features and then object detection using the same. However, the dependency on the kernel’s size and the network’s depth results in fading relationships of latent space features and also are unable to characterize the spatial-contextual bonding of the pixels. Hence, they are unable to procure satisfactory results in complex underwater scenarios. To re-establish this relationship, we propose a unique architecture for underwater object detection where U-Net architecture is considered with the ResNet-50 backbone. Further, the latent space features from the encoder are fed to the decoder through a GraphSage model. GraphSage-based model is explored to reweight the node relationship in non-euclidean space using different aggregator functions and hence characterize the spatio-contextual bonding among the pixels. Further, we explored the dependency on different aggregator functions: mean, max, and LSTM, to evaluate the model’s performance. We evaluated the proposed model on two underwater benchmark databases: F4Knowledge and underwater change detection. The performance of the proposed model is evaluated against eleven state-of-the-art techniques in terms of both visual and quantitative evaluation measures.","PeriodicalId":355438,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"223 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115923285","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}

引用次数: 1

Synthetic Data for Defect Segmentation on Complex Metal Surfaces 复杂金属表面缺陷分割的合成数据

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2023-06-01 DOI: 10.1109/CVPRW59228.2023.00465

Juraj Fulir, Lovro Bosnar, H. Hagen, Petra Gospodnetić

引用次数: 2

Self-supervised Interest Point Detection and Description for Fisheye and Perspective Images 鱼眼和透视图像的自监督兴趣点检测与描述

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2023-06-01 DOI: 10.1109/CVPRW59228.2023.00691

Marcela Mera-Trujillo, Shivang Patel, Yu Gu, Gianfranco Doretto

{"title":"Self-supervised Interest Point Detection and Description for Fisheye and Perspective Images","authors":"Marcela Mera-Trujillo, Shivang Patel, Yu Gu, Gianfranco Doretto","doi":"10.1109/CVPRW59228.2023.00691","DOIUrl":"https://doi.org/10.1109/CVPRW59228.2023.00691","url":null,"abstract":"Keypoint detection and matching is a fundamental task in many computer vision problems, from shape reconstruction, to structure from motion, to AR/VR applications and robotics. It is a well-studied problem with remarkable successes such as SIFT, and more recent deep learning approaches. While great robustness is exhibited by these techniques with respect to noise, illumination variation, and rigid motion transformations, less attention has been placed on image distortion sensitivity. In this work, we focus on the case when this is caused by the geometry of the cameras used for image acquisition, and consider the keypoint detection and matching problem between the hybrid scenario of a fisheye and a projective image. We build on a state-of-the-art approach and derive a self-supervised procedure that enables training an interest point detector and descriptor network. We also collected two new datasets for additional training and testing in this unexplored scenario, and we demonstrate that current approaches are suboptimal because they are designed to work in traditional projective conditions, while the proposed approach turns out to be the most effective.","PeriodicalId":355438,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132346141","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}

引用次数: 1

Improving Automatic Target Recognition in Low Data Regime using Semi-Supervised Learning and Generative Data Augmentation 基于半监督学习和生成数据增强的低数据区自动目标识别

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2023-06-01 DOI: 10.1109/CVPRW59228.2023.00521

Fadoua Khmaissia, H. Frigui

{"title":"Improving Automatic Target Recognition in Low Data Regime using Semi-Supervised Learning and Generative Data Augmentation","authors":"Fadoua Khmaissia, H. Frigui","doi":"10.1109/CVPRW59228.2023.00521","DOIUrl":"https://doi.org/10.1109/CVPRW59228.2023.00521","url":null,"abstract":"We propose a new strategy to improve Automatic Target Recognition (ATR) from infrared (IR) images by leveraging semi-supervised learning and generative data augmentation.Our approach is twofold: first, we use an automatic detector’s outputs to augment the existing labeled and unlabeled data. Second, we introduce a confidence-guided data generative augmentation technique that focuses on learning from the most challenging regions of the feature space, to generate synthetic data which can be used as extra unlabeled data.We evaluate the proposed approach on a public dataset with IR imagery of civilian and military vehicles. We show that yields substantial percentage improvements in ATR performance relative to both the baseline fully supervised model trained using the existing data only, and a semi-supervised model trained without generative data augmentation. For instance, for the most challenging data partition, our method achieves a relative increase of 29.51% over the baseline fully supervised model and a relative improvement of 2.59% over the semi-supervised model. These results demonstrate the effectiveness of our approach in low-data regimes, where labeled data is limited or expensive to obtain.","PeriodicalId":355438,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130165979","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}

引用次数: 0

M3ED: Multi-Robot, Multi-Sensor, Multi-Environment Event Dataset 多机器人，多传感器，多环境事件数据集

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2023-06-01 DOI: 10.1109/CVPRW59228.2023.00419

Kenneth Chaney, Fernando Cladera Ojeda, Ziyun Wang, Anthony Bisulco, M. A. Hsieh, C. Korpela, Vijay R. Kumar, C. J. Taylor, Kostas Daniilidis

引用次数: 5