检索结果-内蒙古大学图书馆

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

作者： Wu, Hai Wen, Chenglu Shi, Shaoshuai Li, Xin Wang, Cheng Xiamen Univ Xiamen Peoples R China Max Planck Inst Munich Germany Texas A&M Univ College Stn TX 77843 USA

ISBN: (纸本)9798350301298

Recently, virtual/pseudo-point-based 3D object detection that seamlessly fuses RGB images and LiDAR data by depth completion has gained great attention. However, virtual points generated from an image are very dense, introducing a huge amount of redundant computation during detection. Meanwhile, noises brought by inaccurate depth completion significantly degrade detection precision. This paper proposes a fast yet effective backbone, termed VirConvNet, based on a new operator VirConv (Virtual Sparse Convolution), for virtual-point-based 3D object detection. VirConv consists of two key designs: (1) StVD (Stochastic Voxel Discard) and (2) NRConv (Noise-Resistant Sub-manifold Convolution). StVD alleviates the computation problem by discarding large amounts of nearby redundant voxels. NRConv tackles the noise problem by encoding voxel features in both 2D image and 3D LiDAR space. By integrating VirConv, we first develop an efficient pipeline VirConv-L based on an early fusion design. Then, we build a high-precision pipeline VirConv-T based on a transformed refinement scheme. Finally, we develop a semi-supervised pipeline VirConv-S based on a pseudo-label framework. On the KITTI car 3D detection test leaderboard, our VirConv-L achieves 85% AP with a fast running speed of 56ms. Our VirConv-T and VirConv-S attains a high-precision of 86.3% and 87.2% AP, and currently rank 2nd and 1st(1), respectively. The code is available at https://***/hailanyi/VirConv.

关键词： detection recognition: Categorization retrieval

来源：评论

学校读者我要写书评

暂无评论

PIRLNav: Pretraining with Imitation and RL Finetuning for OBJECTNAV

PIRLNav: Pretraining with Imitation and RL Finetuning for OB...

引用

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

作者： Ramrakhya, Ram Batra, Dhruv Wijmans, Erik Das, Abhishek Georgia Inst Technol Atlanta GA 30332 USA Meta AI FAIR Menlo Pk CA USA

ISBN: (纸本)9798350301298

We study ObjectGoal Navigation - where a virtual robot situated in a new environment is asked to navigate to an object. Prior work [1] has shown that imitation learning (IL) using behavior cloning (BC) on a dataset of human demonstrations achieves promising results. However, this has limitations - 1) BC policies generalize poorly to new states, since the training mimics actions not their consequences, and 2) collecting demonstrations is expensive. On the other hand, reinforcement learning (RL) is trivially scalable, but requires careful reward engineering to achieve desirable behavior. We present PIRLNav, a two-stage learning scheme for BC pretraining on human demonstrations followed by RL-finetuning. This leads to a policy that achieves a success rate of 65.0% on OBJECTNAV (+5.0% absolute over previous state-of-the-art). Using this BC -> RL training recipe, we present a rigorous empirical analysis of design choices. First, we investigate whether human demonstrations can be replaced with 'free' (automatically generated) sources of demonstrations, e.g. shortest paths (SP) or task-agnostic frontier exploration (FE) trajectories. We find that BC -> RL on human demonstrations outperforms BC -> RL on SP and FE trajectories, even when controlled for the same BC-pretraining success on TRAIN, and even on a subset of VAL episodes where BC-pretraining success favors the SP or FE policies. Next, we study how RL-finetuning performance scales with the size of the BC pretraining dataset. We find that as we increase the size of the BC-pretraining dataset and get to high BC accuracies, the improvements from RL-finetuning are smaller, and that 90% of the performance of our best BC -> RL policy can be achieved with less than half the number of BC demonstrations. Finally, we analyze failure modes of our OBJECTNAV policies, and present guidelines for further improving them. Project page: ***/projects/pirlnav.

关键词： Embodied vision: Active agents simulation

来源：评论

学校读者我要写书评

暂无评论

Cloud-Device Collaborative Adaptation to Continual Changing Environments in the Real-world

Cloud-Device Collaborative Adaptation to Continual Changing ...

引用

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

作者： Gan, Yulu Pan, Mingjie Zhang, Rongyu Ling, Zijian Zhao, Lingran Liu, Jiaming Zhang, Shanghang Peking Univ Sch Comp Sci Natl Key Lab Multimedia Informat Proc Beijing Peoples R China Chinese Univ Hong Kong Shenzhen Peoples R China Imperial Coll London London England

ISBN: (纸本)9798350301298

When facing changing environments in the real world, the lightweight model on client devices suffers from severe performance drops under distribution shifts. The main limitations of the existing device model lie in (1) unable to update due to the computation limit of the device, (2) the limited generalization ability of the lightweight model. Meanwhile, recent large models have shown strong generalization capability on the cloud while they can not be deployed on client devices due to poor computation constraints. To enable the device model to deal with changing environments, we propose a new learning paradigm of Cloud-Device Collaborative Continual Adaptation, which encourages collaboration between cloud and device and improves the generalization of the device model. Based on this paradigm, we further propose an Uncertainty-based Visual Prompt Adapted (U-VPA) teacher-student model to transfer the generalization capability of the large model on the cloud to the device model. Specifically, we first design the Uncertainty Guided Sampling (UGS) to screen out challenging data continuously and transmit the most out-of-distribution samples from the device to the cloud. Then we propose a Visual Prompt Learning Strategy with Uncertainty guided updating (VPLU) to specifically deal with the selected samples with more distribution shifts. We transmit the visual prompts to the device and concatenate them with the incoming data to pull the device testing distribution closer to the cloud training distribution. We conduct extensive experiments on two object detection datasets with continually changing environments. Our proposed U-VPA teacher-student framework outperforms previous state-of-the-art test time adaptation and device-cloud collaboration methods. The code and datasets will be released.

关键词： vision applications and systems

来源：评论

学校读者我要写书评

暂无评论

Second Edition FRCSyn Challenge at cvpr 2024: Face recognition Challenge in the Era of Synthetic Data

Second Edition FRCSyn Challenge at CVPR 2024: Face Recogniti...

引用

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

作者： DeAndres-Tame, Ivan Tolosana, Ruben Melzi, Pietro Vera-Rodriguez, Ruben Kim, Minchul Rathgeb, Christian Liu, Xiaoming Morales, Aythami Fierrez, Julian Ortega-Garcia, Javier Zhong, Zhizhou Huang, Yuge Mi, Yuxi Ding, Shouhong Zhou, Shuigeng He, Shuai Fu, Lingzhi Cong, Heng Zhang, Rongyu Xiao, Zhihong Smirnov, Evgeny Pimenov, Anton Grigorev, Aleksei Timoshenko, Denis Asfaw, Kaleb Mesfin Low, Cheng Yaw Liu, Hao Wang, Chuyi Zuo, Qing He, Zhixiang Shahreza, Hatef Otroshi George, Anjith Unnervik, Alexander Rahimi, Parsa Marcel, Ebastien Neto, Pedro C. Huber, Marco Kolf, Jan Niklas Damer, Naser Boutros, Fadi Cardoso, Jaime S. Sequeira, Ana F. Atzori, Andrea Fenu, Gianni Marras, Mirko Struc, Vitomir Yu, Jiang Li, Zhangjie Li, Jichun Zhao, Weisong Lei, Zhen Zhu, Xiangyu Zhang, Xiao-Yu Biesseck, Bernardo Vidal, Pedro Coelho, Luiz Granada, Roger Menotti, David Univ Autonoma Madrid Madrid Spain Michigan State Univ E Lansing MI 48824 USA Hsch Darmstadt Darmstadt Germany Fudan Univ Shanghai Peoples R China Tencent Youtu Lab Shanghai Peoples R China Netease Inc Interact Entertainment Grp Guangzhou Peoples R China ID R&D Inc New York NY USA Korea Adv Inst Sci & Technol Daejeon South Korea Inst for Basic Sci Korea Daejeon South Korea China Telecom AI Beijing Peoples R China Idiap Res Inst Martigny Switzerland Ecole Polytech Fed Lausanne Lausanne Switzerland Univ Lausanne Lausanne Switzerland INESC TEC Porto Portugal Univ Porto Porto Portugal Fraunhofer IGD Darmstadt Germany Univ Cagliari Cagliari Italy Univ Ljubljana Ljubljana Slovenia Samsung Elect China R&D Ctr Shenzhen Peoples R China Univ Sci & Technol Hefei Peoples R China Chinese Acad Sci IIE Beijing Peoples R China CASIA MAIS Shanghai Peoples R China Univ Fed Parana Curitiba Parana Brazil Fed Inst Mato Grosso Cuiaba Brazil Unico IdTech Sao Paulo Brazil

ISBN: (纸本)9798350365474

Synthetic data is gaining increasing relevance for training machine learning models. This is mainly motivated due to several factors such as the lack of real data and intra-class variability, time and errors produced in manual labeling, and in some cases privacy concerns, among others. This paper presents an overview of the 2(nd) edition of the Face recognition Challenge in the Era of Synthetic Data (FRCSyn) organized at cvpr 2024. FRCSyn aims to investigate the use of synthetic data in face recognition to address current technological limitations, including data privacy concerns, demographic biases, generalization to novel scenarios, and performance constraints in challenging situations such as aging, pose variations, and occlusions. Unlike the 1(st) edition, in which synthetic data from DCFace and GANDiffFace methods was only allowed to train face recognition systems, in this 2(nd) edition we propose new subtasks that allow participants to explore novel face generative methods. The outcomes of the 2(nd) FRCSyn Challenge, along with the proposed experimental protocol and benchmarking contribute significantly to the application of synthetic data to face recognition.

关键词： Benchmarking Biometrics recognition Demographic Bias Face recognition FRCSyn Generative AI Privacy Synthetic Data

来源：评论

学校读者我要写书评

暂无评论

AI-Synthesized Voice Detection Using Neural Vocoder Artifacts

AI-Synthesized Voice Detection Using Neural Vocoder Artifact...

引用

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

作者： Sun, Chengzhe Jia, Shan Hou, Shuwei Lyu, Siwei SUNY Buffalo Buffalo NY 14260 USA

ISBN: (纸本)9798350302493

Advancements in AI-synthesized human voices have created a growing threat of impersonation and disinformation, making it crucial to develop methods to detect synthetic human voices. This study proposes a new approach to identifying synthetic human voices by detecting artifacts of vocoders in audio signals. Most DeepFake audio synthesis models use a neural vocoder, a neural network that generates waveforms from temporal-frequency representations like mel-spectrograms. By identifying neural vocoder processing in audio, we can determine if a sample is synthesized. To detect synthetic human voices, we introduce a multi-task learning framework for a binary-class RawNet2 model that shares the feature extractor with a vocoder identification module. By treating vocoder identification as a pretext task, we constrain the feature extractor to focus on vocoder artifacts and provide discriminative features for the final binary classifier. Our experiments show that the improved RawNet2 model based on vocoder identification achieves high classification performance on the binary task overall. Codes and data can be found at https:// github. com/ csun22/SyntheticVoice-Detection- Vocoder-Artifacts.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Introduction to the Special Section of cvpr 2017

引用

ieee TRANSACTIONS ON pattern ANALYSIS AND MACHINE INTELLIGENCE 2022年第12期44卷 8702-8703页

作者： Liu, Yanxi Rehg, James M. Taylor, Camillo J. Wu, Ying Penn State Univ Sch EECS State Coll PA 16801 USA Georgia Inst Technol Sch Interact Comp Atlanta GA 30332 USA Univ Penn Comp & Informat Sci Dept State Coll PA 16801 USA Northwestern Univ Elect Engn & Comp Sci Dept Evanston IL 60208 USA

The papers in this special section were presented at the computer vision and pattern recognition conference.

关键词： Special Issues And Sections Meetings computer vision pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Hierarchical discriminative learning improves visual representations of biomedical microscopy

Hierarchical discriminative learning improves visual represe...

引用

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

作者： Jiang, Cheng Hou, Xinhai Kondepudi, Akhil Chowdury, Asadur Freudiger, Christian W. Orringer, Daniel A. Lee, Honglak Hollon, Todd C. Univ Michigan Ann Arbor MI 48109 USA Invenio Imaging Santa Clara CA USA NYU New York NY USA LG AI Res Seoul South Korea

ISBN: (纸本)9798350301298

Learning high-quality, self-supervised, visual representations is essential to advance the role of computer vision in biomedical microscopy and clinical medicine. Previous work has focused on self-supervised representation learning (SSL) methods developed for instance discrimination and applied them directly to image patches, or fields-of-view, sampled from gigapixel whole-slide images (WSIs) used for cancer diagnosis. However, this strategy is limited because it (1) assumes patches from the same patient are independent, (2) neglects the patient-slide-patch hierarchy of clinical biomedical microscopy, and (3) requires strong data augmentations that can degrade downstream performance. Importantly, sampled patches from WSIs of a patient's tumor are a diverse set of image examples that capture the same underlying cancer diagnosis. This motivated HiDisc, a data-driven method that leverages the inherent patient-slide-patch hierarchy of clinical biomedical microscopy to define a hierarchical discriminative learning task that implicitly learns features of the underlying diagnosis. HiDisc uses a self-supervised contrastive learning framework in which positive patch pairs are defined based on a common ancestry in the data hierarchy, and a unified patch, slide, and patient discriminative learning objective is used for visual SSL. We benchmark HiDisc visual representations on two vision tasks using two biomedical microscopy datasets, and demonstrate that (1) HiDisc pretraining outperforms current state-of-the-art self-supervised pretraining methods for cancer diagnosis and genetic mutation prediction, and (2) HiDisc learns high-quality visual representations using natural patch diversity without strong data augmentations. [GRAPHICS] .

关键词： cell microscopy Medical and biological vision

来源：评论

学校读者我要写书评

暂无评论

An Iterative Quantum Approach for Transformation Estimation from Point Sets

An Iterative Quantum Approach for Transformation Estimation ...

引用

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

作者： Meli, Natacha Kuete Mannel, Florian Lellmann, Jan Univ Lubeck Inst Math & Image Comp Lubeck Germany

ISBN: (纸本)9781665469463

We propose an iterative method for estimating rigid transformations from point sets using adiabatic quantum computation. Compared to existing quantum approaches, our method relies on an adaptive scheme to solve the problem to high precision, and does not suffer from inconsistent rotation matrices. Experimentally, our method performs robustly on several 2D and 3D datasets even with high outlier ratio.

关键词： computer vision Three-dimensional displays Annealing Estimation Quantum annealing pattern recognition Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Adaptive Zone-aware Hierarchical Planner for vision-Language Navigation

Adaptive Zone-aware Hierarchical Planner for Vision-Language...

引用

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

作者： Gao, Chen Peng, Xingyu Yan, Mi Wang, He Yang, Lirong Ren, Haibing Li, Hongsheng Liu, Si Beihang Univ Inst Artificial Intelligence Beijing Peoples R China Beihang Univ Hangzhou Innovat Inst Beijing Peoples R China Peking Univ CFCS Beijing Peoples R China Peking Univ Sch EECS Beijing Peoples R China Meituan Beijing Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9798350301298

The task of vision-Language Navigation (VLN) is for an embodied agent to reach the global goal according to the instruction. Essentially, during navigation, a series of subgoals need to be adaptively set and achieved, which is naturally a hierarchical navigation process. However, previous methods leverage a single-step planning scheme, i.e., directly performing navigation action at each step, which is unsuitable for such a hierarchical navigation process. In this paper, we propose an Adaptive Zone-aware Hierarchical Planner (AZHP) to explicitly divides the navigation process into two heterogeneous phases, i.e., sub-goal setting via zone partition/selection (high-level action) and subgoal executing (low-level action), for hierarchical planning. Specifically, AZHP asynchronously performs two levels of action via the designed State-Switcher Module (SSM). For high-level action, we devise a Scene-aware adaptive Zone Partition (SZP) method to adaptively divide the whole navigation area into different zones on-the-fly. Then the Goal-oriented Zone Selection (GZS) method is proposed to select a proper zone for the current sub-goal. For low-level action, the agent conducts navigation-decision multi-steps in the selected zone. Moreover, we design a Hierarchical RL (HRL) strategy and auxiliary losses with curriculum learning to train the AZHP framework, which provides effective supervision signals for each stage. Extensive experiments demonstrate the superiority of our proposed method, which achieves state-of-the-art performance on three VLN benchmarks (REVERIE, SOON, R2R).

关键词： language reasoning vision

来源：评论

学校读者我要写书评

暂无评论

Gradient Attention Balance Network: Mitigating Face recognition Racial Bias via Gradient Attention

Gradient Attention Balance Network: Mitigating Face Recognit...

引用

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

作者： Huang, Linzhi Wang, Mei Liang, Jiahao Deng, Weihong Shi, Hongzhi Wen, Dongchao Zhang, Yingjie Zhao, Jian Inspur Elect Informat Ind Co Ltd Jinan Peoples R China Shandong Mass Informat Technol Res Inst Qingdao Peoples R China

ISBN: (纸本)9798350302493

Although face recognition has made impressive progress in recent years, we ignore the racial bias of the recognition system when we pursue a high level of accuracy. Previous work found that for different races, face recognition networks focus on different facial regions, and the sensitive regions of darker-skinned people are much smaller. Based on this discovery, we propose a new de-bias method based on gradient attention, called Gradient Attention Balance Network (GABN). Specifically, we use the gradient attention map (GAM) of the face recognition network to track the sensitive facial regions and make the GAMs of different races tend to be consistent through adversarial learning. This method mitigates the bias by making the network focus on similar facial regions. In addition, we also use masks to erase the Top-N sensitive facial regions, forcing the network to allocate its attention to a larger facial region. This method expands the sensitive region of darker-skinned people and further reduces the gap between GAM of darker-skinned people and GAM of Caucasians. Extensive experiments show that GABN successfully mitigates racial bias in face recognition and learns more balanced performance for people of different races.

关键词： Face 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：