检索结果-内蒙古大学图书馆

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Zhang, HaiYang Xing, XiMing Liu, Liang Beijing Univ Posts & Telecommun Sch Comp Sci Beijing Peoples R China

ISBN: (纸本)9781665445092

Unreliable labels derived from large-scale dataset prevent neural networks from fully exploring the data. Existing methods of learning with noisy labels primarily take noise-cleaning-based and sample-selection-based methods. However, for numerous studies on account of the above two views, selected samples cannot take full advantage of all data points and cannot represent actual distribution of categories, in particular if label annotation is corrupted. In this paper, we start from a different perspective and propose a robust learning algorithm called DualGraph, which aims to capture structural relations among labels at two different levels with graph neural networks including instance-level and distribution-level relations. Specifically, the instance-level relation utilizes instance similarity characterize sample category, while the distribution-level relation describes instance similarity distribution from each sample to all other samples. Since the distribution-level relation is robust to label noise, our network propagates it as supervised signals to refine instance-level similarity. Combining two level relations, we design an end-to-end training paradigm to counteract noisy labels while generating reliable predictions. We conduct extensive experiments on the noisy CIFAR-10 dataset, CIFAR-100 dataset, and the Clothing1M dataset. The results demonstrate the advantageous performance of the proposed method in comparison to state-of-the-art baselines.

关键词： Training computer vision Recurrent neural networks Reliability engineering Graph neural networks Robustness pattern recognition

来源：评论

学校读者我要写书评

暂无评论

RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening

RobustNet: Improving Domain Generalization in Urban-Scene Se...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Choi, Sungha Jung, Sanghun Yun, Huiwon Kim, Joanne T. Kim, Seungryong Choo, Jaegul LG AI Res Seoul South Korea Korea Adv Inst Sci & Technol Daejeon South Korea Korea Univ Seoul South Korea Sogang Univ Seoul South Korea

ISBN: (纸本)9781665445092

Enhancing the generalization capability of deep neural networks to unseen domains is crucial for safety-critical applications in the real world such as autonomous driving. To address this issue, this paper proposes a novel instance selective whitening loss to improve the robustness of the segmentation networks for unseen domains. Our approach disentangles the domain-specific style and domain-invariant content encoded in higher-order statistics (i.e., feature covariance) of the feature representations and selectively removes only the style information causing domain shift. As shown in Fig. 1, our method provides reasonable predictions for (a) low-illuminated, (b) rainy, and (c) unseen structures. These types of images are not included in the training dataset, where the baseline shows a significant performance drop, contrary to ours. Being simple yet effective, our approach improves the robustness of various backbone networks without additional computational cost. We conduct extensive experiments in urban-scene segmentation and show the superiority of our approach to existing work. Our code is available at this link(1).

关键词： Training Deep learning Image segmentation computer vision Codes Robustness pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Towards Evaluating and Training Verifiably Robust Neural Networks

Towards Evaluating and Training Verifiably Robust Neural Net...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Lyu, Zhaoyang Guo, Minghao Wu, Tong Xu, Guodong Zhang, Kehuan Lin, Dahua SenseTime CUHK Joint Lab Hong Kong Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China Ctr Perceptual & Interact Intelligence Hong Kong Peoples R China

ISBN: (纸本)9781665445092

Recent works have shown that interval bound propagation (!BP) can be used to train verifiably robust neural networks. Reseachers observe an intriguing phenomenon on these IBP trained networks: CROWN, a bounding method based on tight linear relaxation, often gives very loose bounds on these networks. We also observe that most neurons become dead during the IBP training process, which could hurt the representation capability of the network. In this paper, we study the relationship between IBP and CROWN, and prove that CROWN is always tighter than !BP when choosing appropriate bounding lines. We further propose a relaxed version of CROWN, linear bound propagation (LBP), that can be used to verify large networks to obtain lower verified errors than IBP We also design a new activation function, parameterized ramp function (ParamRamp), which has more diversity of neuron status than ReLU. We conduct extensive experiments on MNIST, CIFAR-10 and Tiny-ImageNet with ParamRamp activation and achieve state-of-the-art verified robustness. Code is available at https://github com/ZhaoyangLyu/VerifiablyRobustNN.

关键词： Training computer vision Codes Scalability Neurons Robustness pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Self-generated Defocus Blur Detection via Dual Adversarial Discriminators

Self-generated Defocus Blur Detection via Dual Adversarial D...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Zhao, Wenda Shang, Cai Lu, Huchuan Dalian Univ Technol Sch Informat & Commun Engn Dalian Peoples R China

ISBN: (纸本)9781665445092

Although existing fully-supervised defocus blur detection (DBD) models significantly improve performance, training such deep models requires abundant pixel-level manual annotation, which is highly time-consuming and error-prone. Addressing this issue, this paper makes an effort to train a deep DBD model without using any pixel-level annotation. The core insight is that a defocus blur region/focused clear area can be arbitrarily pasted to a given realistic full blurred image/full clear image without affecting the judgment of the full blurred image/full clear image. Specifically, we train a generator G in an adversarial manner against dual discriminators D-c and D-b. G learns to produce a DBD mask that generates a composite clear image and a composite blurred image through copying the focused area and unfocused region from corresponding source image to another full clear image and full blurred image. Then, D-c and D-b can not distinguish them from realistic full clear image and full blurred image simultaneously, achieving a self-generated DBD by an implicit manner to define what a defocus blur area is. Besides, we propose a bilateral triplet-excavating constraint to avoid the degenerate problem caused by the case one discriminator defeats the other one. Comprehensive experiments on two widely-used DBD datasets demonstrate the superiority of the proposed approach. Source codes are available at: https://***/shangcail/SG.

关键词： Training computer vision Codes Annotations Manuals Generators pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Deep Bingham Networks: Dealing with Uncertainty and Ambiguity in Pose Estimation

引用

INTERNATIONAL JOURNAL OF computer vision 2022年第7期130卷 1627-1654页

作者： Deng, Haowen Bui, Mai Navab, Nassir Guibas, Leonidas Ilic, Slobodan Birdal, Tolga Tech Univ Munich Informat Munich Germany Corp Technol Siemens AG Munich Germany Stanford Univ Dept Comp Sci Stanford CA 94305 USA

In this work, we introduce Deep Bingham Networks (DBN), a generic framework that can naturally handle pose-related uncertainties and ambiguities arising in almost all real life applications concerning 3D data. While existing works strive to find a single solution to the pose estimation problem, we make peace with the ambiguities causing high uncertainty around which solutions to identify as the best. Instead, we report a family of poses which capture the nature of the solution space. DBN extends the state of the art direct pose regression networks by (i) a multi-hypotheses prediction head which can yield different distribution modes;and (ii) novel loss functions that benefit from Bingham distributions on rotations. This way, DBN can work both in unambiguous cases providing uncertainty information, and in ambiguous scenes where an uncertainty per mode is desired. On a technical front, our network regresses continuous Bingham mixture models and is applicable to both 2D data such as images and to 3D data such as point clouds. We proposed new training strategies so as to avoid mode or posterior collapse during training and to improve numerical stability. Our methods are thoroughly tested on two different applications exploiting two different modalities: (i) 6D camera relocalization from images;and (ii) object pose estimation from 3D point clouds, demonstrating decent advantages over the state of the art. For the former we contributed our own dataset composed of five indoor scenes where it is unavoidable to capture images corresponding to views that are hard to uniquely identify. For the latter we achieve the top results especially for symmetric objects of ModelNet dataset (Wu et al., in: Proceedings of the ieee conference on computer vision and pattern recognition, pp 1912-1920, 2015). The code and dataset accompanying this paper is provided under https://***.

关键词： 3D computer vision Point clouds Camera relocalization 6D Camera pose Object pose Rotation Bingham distribution Posterior distribution Ambiguity Uncertainty Uncertainty estimation

来源：评论

学校读者我要写书评

暂无评论

RSG: A Simple but Effective Module for Learning Imbalanced Datasets

RSG: A Simple but Effective Module for Learning Imbalanced D...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Wang, Jianfeng Lukasiewicz, Thomas Hu, Xiaolin Cai, Jianfei Xu, Zhenghua Univ Oxford Oxford England Tsinghua Univ Beijing Peoples R China Monash Univ Melbourne Vic Australia Hebei Univ Technol Tianjin Peoples R China

ISBN: (纸本)9781665445092

Imbalanced datasets widely exist in practice and are a great challenge for training deep neural models with a good generalization on infrequent classes. In this work, we propose a new rare-class sample generator (RSG) to solve this problem. RSG aims to generate some new samples for rare classes during training, and it has in particular the following advantages: (1) it is convenient to use and highly versatile, because it can be easily integrated into any kind of convolutional neural network, and it works well when combined with different loss functions, and (2) it is only used during the training phase, and therefore, no additional burden is imposed on deep neural networks during the testing phase. In extensive experimental evaluations, we verify the effectiveness of RSG. Furthermore, by leveraging RSG, we obtain competitive results on Imbalanced CIFAR and new state-of-the-art results on Places-LT, ImageNet-LT, and iNaturalist 2018. The source code is available at https://***-Wang/RSG.

关键词： Training Deep learning computer vision Codes Generators pattern recognition Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Iso-Points: Optimizing Neural Implicit Surfaces with Hybrid Representations

Iso-Points: Optimizing Neural Implicit Surfaces with Hybrid ...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Wang Yifan Wu, Shihao Oztireli, Cengiz Sorkine-Hornung, Olga Swiss Fed Inst Technol Zurich Switzerland Univ Cambridge Cambridge England

ISBN: (数字)9781665445092

ISBN: (纸本)9781665445092

Neural implicit functions have emerged as a powerful representation for surfaces in 3D. Such a function can encode a high quality surface with intricate details into the parameters of a deep neural network. However, optimizing for the parameters for accurate and robust reconstructions remains a challenge, especially when the input data is noisy or incomplete. In this work, we develop a hybrid neural surface representation that allows us to impose geometry-aware sampling and regularization, which significantly improves the fidelity of reconstructions. We propose to use iso-points as an explicit representation for a neural implicit function. These points are computed and updated on-the-fly during training to capture important geometric features and impose geometric constraints on the optimization. We demonstrate that our method can be adopted to improve state-of-the-art techniques for reconstructing neural implicit surfaces from multi-view images or point clouds. Quantitative and qualitative evaluations show that, compared with existing sampling and optimization methods, our approach allows faster convergence, better generalization, and accurate recovery of details and topology.

关键词： Training Deep learning Surface reconstruction Three-dimensional displays Optimization methods Topology pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Generalizing to the Open World: Deep Visual Odometry with Online Adaptation

Generalizing to the Open World: Deep Visual Odometry with On...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Li, Shunkai Wu, Xin Cao, Yingdian Zha, Hongbin Peking Univ Sch EECS Key Lab Machine Percept MOE PKU SenseTime Machine Vis Joint Lab Beijing Peoples R China

ISBN: (数字)9781665445092

ISBN: (纸本)9781665445092

Despite learning-based visual odometry (VO) has shown impressive results in recent years, the pretrained networks may easily collapse in unseen environments. The large domain gap between training and testing data makes them difficult to generalize to new scenes. In this paper, we propose an online adaptation framework for deep VO with the assistance of scene-agnostic geometric computations and Bayesian inference. In contrast to learning-based pose estimation, our method solves pose from optical flow and depth while the single-view depth estimation is continuously improved with new observations by online learned uncertainties. Meanwhile, an online learned photometric uncertainty is used for further depth and pose optimization by a differentiable Gauss-Newton layer. Our method enables fast adaptation of deep VO networks to unseen environments in a self-supervised manner. Extensive experiments including Cityscapes to KITTI and outdoor KITTI to indoor TUM demonstrate that our method achieves state-of-the-art generalization ability among self-supervised VO methods.

关键词： Training Optical filters Uncertainty Pose estimation Bayes methods pattern recognition Optimization

来源：评论

学校读者我要写书评

暂无评论

Fast GraspNeXt: A Fast Self-Attention Neural Network Architecture for Multi-task Learning in computer vision Tasks for Robotic Grasping on the Edge

Fast GraspNeXt: A Fast Self-Attention Neural Network Archite...

引用

ieee computer society conference on computer vision and pattern recognition Workshops (CVPRW)

作者： Alexander Wong Yifan Wu Saad Abbasi Saeejith Nair Yuhao Chen Mohammad Javad Shafiee Vision and Image Processing Research Group University of Waterloo Waterloo Artificial Intelligence Institute Waterloo ON DarwinAI Corp. Waterloo ON

Multi-task learning has shown considerable promise for improving the performance of deep learning-driven vision systems for the purpose of robotic grasping. However, high architectural and computational complexity can result in poor suitability for deployment on embedded devices that are typically leveraged in robotic arms for real-world manufacturing and warehouse environments. As such, the design of highly efficient multi-task deep neural network architectures tailored for computer vision tasks for robotic grasping on the edge is highly desired for widespread adoption in manufacturing environments. Motivated by this, we propose Fast GraspNeXt, a fast self-attention neural network architecture tailored for embedded multi-task learning in computer vision tasks for robotic grasping. To build Fast GraspNeXt, we leverage a generative network architecture search strategy with a set of architectural constraints customized to achieve a strong balance between multitask learning performance and embedded inference efficiency. Experimental results on the MetaGraspNet benchmark dataset show that the Fast GraspNeXt network design achieves the highest performance (average precision (AP), accuracy, and mean squared error (MSE)) across multiple computer vision tasks when compared to other efficient multi-task network architecture designs, while having only 17.8M parameters (about >5× smaller), 259 GFLOPs (as much as >5× lower) and as much as >3.15× faster on a NVIDIA Jetson TX2 embedded processor.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural Feature Search for RGB-Infrared Person Re-Identification

Neural Feature Search for RGB-Infrared Person Re-Identificat...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Chen, Yehansen Wan, Lin Li, Zhihang Jing, Qianyan Sun, Zongyuan China Univ Geosci Sch Geog & Informat Engn Wuhan Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China

ISBN: (纸本)9781665445092

RGB-Infrared person re-identification (RGB-IR ReID) is a challenging cross-modality retrieval problem, which aims at matching the person-of-interest over visible and infrared camera views. Most existing works achieve performance gains through manually-designed feature selection modules, which often require significant domain knowledge and rich experience. In this paper, we study a general paradigm, termed Neural Feature Search (NFS), to automate the process of feature selection. Specifically, NFS combines a dual-level feature search space and a differentiable search strategy to jointly select identity-related cues in coarse-grained channels and fine-grained spatial pixels. This combination allows NFS to adaptively filter background noises and concentrate on informative parts of human bodies in a data-driven manner. Moreover, a cross-modality contrastive optimization scheme further guides NFS to search features that can minimize modality discrepancy whilst maximizing inter-class distance. Extensive experiments on mainstream benchmarks demonstrate that our method outperforms state-of-the-arts, especially achieving better performance on the RegDB dataset with significant improvement of 11.20% and 8.64% in Rank-1 and mAP, respectively.

关键词： computer vision Manuals Benchmark testing Performance gain Feature extraction Search problems pattern recognition

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：