检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Fan, Junkai Wang, Kun Yan, Zhiqiang Chen, Xiang Gao, Shangbing Li, Jun Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China Huaiyin Institute of Technology China

In this paper, we study the challenging problem of simultaneously removing haze and estimating depth from real monocular hazy videos. These tasks are inherently complementary: enhanced depth estimation improves dehazing via the atmospheric scattering model (ASM), while superior dehazing contributes to more accurate depth estimation through the brightness consistency constraint (BCC). To tackle these intertwined tasks, we propose a novel depth-centric learning framework that integrates the ASM model with the BCC constraint. Our key idea is that both ASM and BCC rely on a shared depth estimation network. This network simultaneously exploits adjacent dehazed frames to enhance depth estimation via BCC and uses the refined depth cues to more effectively remove haze through ASM. Additionally, we leverage a non-aligned clear video and its estimated depth to independently regularize the dehazing and depth estimation networks. This is achieved by designing two discriminator networks: DMFIR enhances high-frequency details in dehazed videos, and DMDR reduces the occurrence of black holes in low-texture regions. Extensive experiments demonstrate that the proposed method outperforms current state-of-the-art techniques in both video dehazing and depth estimation tasks, especially in real-world hazy scenes. Project page: https://***/projectpage/DCL/***. Copyright © 2024, The Authors. All rights reserved.

关键词： Demulsification

来源：评论

学校读者我要写书评

暂无评论

Progressive exploration-conformal learning for sparsely annotated object detection in aerial images 24

Progressive exploration-conformal learning for sparsely anno...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Zihan Lu Chenxu Wang Chunyan Xu Xiangwei Zheng Zhen Cui PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Shandong Normal University Jinan China

ISBN: (纸本)9798331314385

The ability to detect aerial objects with limited annotation is pivotal to the development of real-world aerial intelligence systems. In this work, we focus on a demanding but practical sparsely annotated object detection (SAOD) in aerial images, which encompasses a wider variety of aerial scenes with the same number of annotated objects. Although most existing SAOD methods rely on fixed thresholding to filter pseudo-labels for enhancing detector performance, adapting to aerial objects proves challenging due to the imbalanced probabilities/confidences associated with predicted aerial objects. To address this problem, we propose a novel Progressive Exploration-Conformal Learning (PECL) framework to address the SAOD task, which can adaptively perform the selection of high-quality pseudo-labels in aerial images. Specifically, the pseudo-label exploration can be formulated as a decision-making paradigm by adopting a conformal pseudo-label explorer and a multi-clue selection evaluator. The conformal pseudo-label explorer learns an adaptive policy by maximizing the cumulative reward, which can decide how to select these high-quality candidates by leveraging their essential characteristics and inter-instance contextual information. The multi-clue selection evaluator is designed to evaluate the explorer-guided pseudo-label selections by providing an instructive feedback for policy optimization. Finally, the explored pseudo-labels can be adopted to guide the optimization of aerial object detector in a closed-loop progressive fashion. Comprehensive evaluations on two public datasets demonstrate the superiority of our PECL when compared with other state-of-the-art methods in the sparsely annotated aerial object detection task. The code will be available at: https://***/SAOD-research/PECL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FaceFormer: Aggregating Global and Local Representation for Face Hallucination

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2023年第6期33卷 2533-2545页

作者： Wang, Yuanzhi Lu, Tao Zhang, Yanduo Wang, Zhongyuan Jiang, Junjun Xiong, Zixiang Wuhan Inst Technol Hubei Key Lab Intelligent Robot Wuhan 430205 Peoples R China Nanjing Univ Sci & Technol Minist Educ PCA Lab Key Lab Intelligent Percept Syst High Dimens Infor Nanjing 210094 Peoples R China Wuhan Inst Technol Hubei Key Lab Intelligent Robot Wuhan 430205 Peoples R China Hubei Univ Arts & Sci Comp Sch Xiangyang 441053 Peoples R China Wuhan Univ Sch Comp Sci NERCMS Wuhan 430072 Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Harbin 150001 Peoples R China Peng Cheng Lab Shenzhen 518066 Peoples R China Texas A&M Univ Dept Elect & Comp Engn College Stn TX 77843 USA

Recently, face hallucination methods either feed whole face image into convolutional neural networks (CNNs) or utilize extra facial priors (e.g., facial parsing maps and landmarks) to focus on global facial structure and constrain facial texture generation. However, the limited receptive fields of CNNs and inaccurate facial priors will reduce the naturalness and fidelity of restored face. In this paper, we propose a FaceFormer that aggregates global representation of Transformers and local representation of CNNs to maintain the consistency of facial structure while restoring local facial details. The reason for this design is that the Transformer can capture global facial information by exploiting the long-distance visual relation modeling, while the local modeling capability of CNNs can recover fine-grained facial details. Therefore, aggregating these two independent representations can help to maximize their merits and reconstruct high-quality and high-fidelity face images. Experimental results of face reconstruction and recognition verify that the proposed FaceFormer significantly outperforms current state-of-the-arts.

关键词： Face hallucination FaceFormer global repre-sentation local representation

来源：评论

学校读者我要写书评

暂无评论

Spatial and Frequency-Based Feature Reconstruction for Cross-Database Micro-Expression Recognition 27

Spatial and Frequency-Based Feature Reconstruction for Cross...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Feng, Zhi Chen, C.L. Philip Xu, Shiting Zhang, Tong South China University of Technology Engineering Research Center of the Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human Guangdong Provincial Key Laboratory of AI Large Model and Intelligent Cognition Guangzhou China Pazhou Lab Guangzhou China

ISBN: (纸本)9781643685489

The vulnerability of individual-database learned model for Micro-Expression Recognition (MER) has significantly hindered their performance in real-world scenarios. Cross-Database Micro-Expression Recognition (CDMER) aims to enhance the robustness and generalization performance for more complicated situations. Most existing CDMER methods typically attempt to leverage spatial information to eliminate the inevitable domain shift between source and target domains. In this paper, we propose a novel feature space reconstruction model that provides feature space with better generalization for CDMER. Specifically, we introduce the Spatial and Frequency Domain Co-learning (SFDC), a three-branch module, that adaptively exploits the spatial and frequency characteristics of intermediate feature representations, capturing the global and local features of micro-expression adequately. Furthermore, to facilitate the synchronization of two domains, Source and Target Domain Synchronization (STDS) module is employed to guide the alignment of different subspaces simultaneously. Extensive experimental results on the SMIC and CASME II databases demonstrate the effectiveness of the reconstruction and the superiority of our proposed method over state-of-the-art (SOTA) methods. © 2024 The Authors.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance

Driving-Video Dehazing with Non-Aligned Regularization for S...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Junkai Fan Jiangwei Weng Kun Wang Yijun Yang Jianjun Qian Jun Li Jian Yang PCA Lab Nanjing University of Science and Technology China PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Sci. & Tech. The Hong Kong University of Science and Technology Guangzhou

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Real driving-video dehazing poses a significant challenge due to the inherent difficulty in acquiring precisely aligned hazy/clear video pairs for effective model training, especially in dynamic driving scenarios with unpredictable weather conditions. In this paper, we propose a pioneering approach that addresses this challenge through a nonaligned regularization strategy. Our core concept involves identifying clear frames that closely match hazy frames, serving as references to supervise a video dehazing network. Our approach comprises two key components: reference matching and video dehazing. Firstly, we introduce a non-aligned reference frame matching module, leveraging an adaptive sliding window to match high-quality reference frames from clear videos. Video dehazing incorporates flow-guided cosine attention sampler and deformable cosine attention fusion modules to enhance spatial multi-frame alignment and fuse their improved information. To validate our approach, we collect a GoProHazy dataset captured effortlessly with GoPro cameras in diverse rural and urban road environments. Extensive experiments demonstrate the superiority of the proposed method over current state-of-the-art methods in the challenging task of real driving-video dehazing. Project page.

关键词： Training Computer vision Fuses Roads Cameras Safety Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptive Point Cloud Semantic Segmentation 6th

Unsupervised Domain Adaptive Point Cloud Semantic Segmentati...

引用

6th Asian Conference on Pattern Recognition (ACPR)

作者： Bian, Yikai Xie, Jin Qian, Jianjun Nanjing Univ Sci & Technol Sch Comp Sci & Engn Minist Educ PCA LabKey Lab Intelligent Percept & Syst High D Nanjing Peoples R China

ISBN: (纸本)9783031023750;9783031023743

Domain adaptation for point cloud semantic segmentation is important since manually labeling point cloud datasets for each domain are expensive and time-consuming. In this paper, in order to transfer prior knowledge from the labeled source domain to the unlabeled target domain, we propose a novel domain consistency framework for unsupervised domain adaptive point cloud semantic segmentation. Specifically, in our framework, we construct a multi-level feature consistency model to generate the high quality pseudo labels for the unlabeled target domain. In the constructed feature consistency model, we encourage the labels of feature maps of point clouds at different levels to be as consistent as possible. Based on the generated features with rich geometric structure information, we furthermore impose a feature consistency constraint on the feature memory bank of the source domain and target features to develop a feature bank based cycle association model. Thus, benefiting from the developed cycle association model, we can alleviate the domain gap and learn discriminative features of point clouds for semantic segmentation in the target domain. Extensive evaluations on different outdoor scenarios ("vKITTI to SemanticPOSS" and "SynthCity to SemanticPOSS") and indoor scenarios ("S3DIS to ScanNet" ) show that our framework achieves state-of-the-art performance.

关键词： Unsupervised domain adaptation Point cloud semantic segmentation Deep learning for visual perception

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning within Tree Search for Fast Macro Placement 41

Reinforcement Learning within Tree Search for Fast Macro Pla...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Geng, Zijie Wang, Jie Liu, Ziyan Xu, Siyuan Tang, Zhentao Yuan, Mingxuan Hao, Jianye Zhang, Yongdong Wu, Feng CAS Key Laboratory of Technology in GIPAS MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition University of Science and Technology of China China Noah's Ark Lab Huawei China Tianjin University Tianjin China

Macro placement is a crucial step in modern chip design, and reinforcement learning (RL) has recently emerged as a promising technique for improving the placement quality. However, existing RL-based techniques are hindered by their low sample efficiency, requiring numerous online rollouts or substantial offline expert data to achieve bootstrap, which are often impractical in industrial scenarios. To address this challenge, we propose a novel sample-efficient framework, namely EfficientPlace, for fast macro placement. EfficientPlace integrates a global tree search algorithm to strategically direct the optimization process, as well as a RL agent for local policy learning to advance the tree search. Experiments on commonly used benchmarks demonstrate that EfficientPlace achieves remarkable placement quality within a short timeframe, outperforming recent state-of-the-art approaches. Copyright 2024 by the author(s)

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Decoupled Pose Knowledge Distillation 23

Adaptive Decoupled Pose Knowledge Distillation

引用

31st ACM International Conference on Multimedia (MM)

作者： Xu, Jie Zhang, Shanshan Yang, Jian Nanjing Univ Sci & Technol Sch Comp Sci & Engn Key Lab Intelligent Percept & Syst High Dimens In PCA LabMinist Educ Nanjing Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Jiangsu Key Lab Image & Video Understanding Socia Nanjing Peoples R China

ISBN: (纸本)9798400701085

Existing state-of-the-art human pose estimation approaches require heavy computational resources for accurate prediction. One promising technique to obtain an accurate yet lightweight pose estimator is Knowledge Distillation (KD), which distills the pose knowledge from a powerful teacher model to a lightweight student model. However, existing human pose KD methods focus more on designing paired student and teacher network architectures, yet ignore the mechanism of pose knowledge distillation. In this work, we reformulate the human pose KD to a coarse to fine process and decouple the classical KD loss into three terms: Binary keypoint vs. Non-keypoint Distillation (BiKD), keypoint Area Distillation (KAD) and Non-keypoint Area Distillation (NAD). Observing the decoupled formulation, we point out an important limitation of the classical pose KD, i.e. the bias between different loss terms limits the performance gain of the student network. To address the biased knowledge distillation problem, we present a novel KD method named Adaptive Decoupled Pose knowledge Distillation (ADPD), enabling BiKD, KAD and NAD to play their roles more effectively and flexibly. Extensive experiments on two standard human pose datasets, MPII and MS COCO, demonstrate that our proposed method outperforms previous KD methods and is generalizable to different teacher-student pairs. The code will be available at https://***/SuperJay1996/ADPD.

关键词： human pose estimation neural networks knowledge distillation adaptive weighting

来源：评论

学校读者我要写书评

暂无评论

Dual feature disentanglement for face anti-spoofing

引用

PATTERN RECOGNITION 2024年 155卷

作者： Ma, Yimei Qian, Jianjun Li, Jun Yang, Jian Sch Comp Sci & Engn PCA Lab Key Lab Intelligent Percept & Syst High Dimens Inf Minist EducNanjing Univ Sci & Technol Nanjing Peoples R China

Domain generalization for Face Anti-Spoofing (FAS) is increasingly crucial with face attacks across unseen domains. Some existing face anti-spoofing methods aim to disentangle spoof feature for both seen and unseen scenarios. However, it is still a challenging problem to capture spoof feature from facial image, because of spoof pattern are often mixed with various facial attributes such as identity, expression, age and gender. To solve the above problem, we propose a Dual Feature Disentanglement Network (DFDN), which leverages feature projection scheme based on domain-invariant feature in conjunction with rearranging the facial structure to learn spoof feature jointly. Specifically, DFDN introduces the local mask module and domain discriminator to enhance the domain-invariant feature. Based on this, we employ the geometry projection relations to achieve the refined spoof pattern via the feature projection. Meanwhile, we disrupt facial structure to weaken face attributes feature learning and guide CNNs to learn spoof feature. Subsequently, consistent regularization is developed to reduce the gap between the above two kinds of spoof pattern by introducing optimal transport and cosine similarity. Extensive experiments and visualizations demonstrate the advantages of our DFDN over the state -of -the -art methods.

关键词： Face anti-spoofing Feature disentangle Liveness feature Spoof pattern Feature projection

来源：评论

学校读者我要写书评

暂无评论

Towards Better Spherical Sliced-Wasserstein Distance Learning with Data-Adaptive Discriminative Projection Direction 39

Towards Better Spherical Sliced-Wasserstein Distance Learnin...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Hongliang Chen, Shuo Luo, Lei Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China School of Intelligence Science and Technology Nanjing University China

ISBN: (纸本)157735897X

Spherical Sliced-Wasserstein (SSW) has recently been proposed to measure the discrepancy between spherical data distributions in various fields, such as geology, medical domains, computer vision, and deep representation learning. However, in the original SSW, all projection directions are treated equally, which is too idealistic and cannot accurately reflect the importance of different projection directions for various data distributions. To address this issue, we propose a novel data-adaptive Discriminative Spherical Sliced-Wasserstein (DSSW) distance, which utilizes a projected energy function to determine the discriminative projection direction for SSW. In our new DSSW, we introduce two types of projected energy functions to generate the weights for projection directions with complete theoretical guarantees. The first type employs a non-parametric deterministic function that transforms the projected Wasserstein distance into its corresponding weight in each projection direction. This improves the performance of the original SSW distance with negligible additional computational overhead. The second type utilizes a neural network-induced function that learns the projection direction weight through a parameterized neural network based on data projections. This further enhances the performance of the original SSW distance with less extra computational overhead. Finally, we evaluate the performance of our proposed DSSW by comparing it with several state-of-the-art methods across a variety of machine learning tasks, including gradient flows, density estimation on real earth data, and self-supervised learning. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Self-supervised learning

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：