检索结果-内蒙古大学图书馆

Taming Self-Supervised Learning for Presentation Attack Detection: De-Folding and De-Mixing

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kong, Zhe Zhang, Wentian Liu, Feng Luo, Wenhan Liu, Haozhe Shen, Linlin Ramachandra, Raghavendra College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of Cyber Science and Technology Sun Yat-sen University Shenzhen Campus Guangdong Shenzhen518107 China Norwegian University of Science and Technology Gjøvik2818 Norway

Biometric systems are vulnerable to Presentation Attacks (PA) performed using various Presentation Attack Instruments (PAIs). Even though there are numerous Presentation Attack Detection (PAD) techniques based on both deep learning and hand-crafted features, the generalization of PAD for unknown PAI is still a challenging problem. In this work, we empirically prove that the initialization of the PAD model is a crucial factor for the generalization, which is rarely discussed in the community. Based on such observation, we proposed a self-supervised learning-based method, denoted as DF-DM. Specifically, DF-DM is based on a global-local view coupled with De-Folding and De-Mixing to derive the task-specific representation for PAD. During De-Folding, the proposed technique will learn region-specific features to represent samples in a local pattern by explicitly minimizing generative loss. While De-Mixing drives detectors to obtain the instance-specific features with global information for more comprehensive representation by minimizing interpolation-based consistency. Extensive experimental results show that the proposed method can achieve significant improvements in terms of both face and fingerprint PAD in more complicated and hybrid datasets when compared with state-of-the-art methods. When training in CASIA-FASD and Idiap Replay-Attack, the proposed method can achieve an 18.60% Equal Error Rate (EER) in OULU-NPU and MSU-MFSD, exceeding baseline performance by 9.54%. The source code of the proposed technique is available at https://***/kongzhecn/dfdm. Copyright © 2021, The Authors. All rights reserved.

关键词： Supervised learning

MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, David Junhao Li, Kunchang Wang, Yali Chen, Yunpeng Chandra, Shashwat Qiao, Yu Liu, Luoqi Shou, Mike Zheng National University of Singapore Singapore Meitu Inc China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Shanghai AI Laboratory China

Recently, MLP-Like networks have been revived for image recognition. However, whether it is possible to build a generic MLP-Like architecture on video domain has not been explored, due to complex spatial-temporal modeling with large computation burden. To fill this gap, we present an efficient self-attention free backbone, namely MorphMLP, which flexibly leverages the concise Fully-Connected (FC) layer for video representation learning. Specifically, a MorphMLP block consists of two key layers in sequence, i.e., MorphFCs and MorphFCt, for spatial and temporal modeling respectively. MorphFCs can effectively capture core semantics in each frame, by progressive token interaction along both height and width dimensions. Alternatively, MorphFCt can adaptively learn long-term dependency over frames, by temporal token aggregation on each spatial location. With such multi-dimension and multi-scale factorization, our MorphMLP block can achieve a great accuracy-computation balance. Finally, we evaluate our MorphMLP on a number of popular video benchmarks. Compared with the recent state-of-the-art models, MorphMLP significantly reduces computation but with better accuracy, e.g., MorphMLP-S only uses 50% GFLOPs of VideoSwin-T but achieves 0.9% top-1 improvement on Kinetics400, under ImageNet1K pretraining. MorphMLP-B only uses 43% GFLOPs of MViT-B but achieves 2.4% top-1 improvement on SSV2, even though MorphMLP-B is pretrained on ImageNet1K while MViT-B is pretrained on Kinetics400. Moreover, our method adapted to the image domain outperforms previous SOTA MLP-Like architectures. Code is available at https://***/MTLab/MorphMLP. Copyright © 2021, The Authors. All rights reserved.

关键词： Image recognition

Deep Multi-Model Fusion for Single-Image Dehazing

学校读者我要写书评

暂无评论

Deep Multi-Model Fusion for Single-Image Dehazing

International Conference on computer vision (ICCV)

作者： Zijun Deng Lei Zhu Xiaowei Hu Chi-Wing Fu Xuemiao Xu Qing Zhang Jing Qin Pheng-Ann Heng South China University of Technology Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology CAS The Chinese University of Hong Kong State Key Laboratory of Subtropical Building Science Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information Sun Yat-sen University The Hong Kong Polytechnic University CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology CAS

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

This paper presents a deep multi-model fusion network to attentively integrate multiple models to separate layers and boost the performance in single-image dehazing. To do so, we first formulate the attentional feature integration module to maximize the integration of the convolutional neural network (CNN) features at different CNN layers and generate the attentional multi-level integrated features (AMLIF). Then, from the AMLIF, we further predict a haze-free result for an atmospheric scattering model, as well as for four haze-layer separation models, and then fuse the results together to produce the final haze-free image. To evaluate the effectiveness of our method, we compare our network with several state-of-the-art methods on two widely-used dehazing benchmark datasets, as well as on two sets of real-world hazy images. Experimental results demonstrate clear quantitative and qualitative improvements of our method over the state-of-the-arts.

关键词： Atmospheric modeling Predictive models Scattering Computational modeling Neural networks computer vision Solid modeling

Mitigating Artifacts in Real-World Video Super-Resolution Models

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xie, Liangbin Wang, Xintao Shi, Shuwei Gu, Jinjin Dong, Chao Shan, Ying The Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China University of Macau China ARC Lab Tencent PCG China Shenzhen International Graduate School Tsinghua University China The University of Sydney Australia Shanghai Artificial Intelligence Laboratory China

The recurrent structure is a prevalent framework for the task of video super-resolution, which models the temporal dependency between frames via hidden states. When applied to real-world scenarios with unknown and complex degradations, hidden states tend to contain unpleasant artifacts and propagate them to restored frames. In this circumstance, our analyses show that such artifacts can be largely alleviated when the hidden state is replaced with a cleaner counterpart. Based on the observations, we propose a Hidden State Attention (HSA) module to mitigate artifacts in real-world video super-resolution. Specifically, we first adopt various cheap filters to produce a hidden state pool. For example, Gaussian blur filters are for smoothing artifacts while sharpening filters are for enhancing details. To aggregate a new hidden state that contains fewer artifacts from the hidden state pool, we devise a Selective Cross Attention (SCA) module, in which the attention between input features and each hidden state is calculated. Equipped with HSA, our proposed method, namely FastRealVSR, is able to achieve 2× speedup while obtaining better performance than Real-BasicVSR. Codes will be available at https://***/TencentARC/FastRealVSR. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

Direct Shooting Method for Numerical Optimal Control: A Modified Transcription Approach

学校读者我要写书评

暂无评论

Direct Shooting Method for Numerical Optimal Control: A Modi...

European Control Conference (ECC)

作者： Jiawei Tang Yuxing Zhong Pengyu Wang Xingzhou Chen Shuang Wu Ling Shi Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Water Bay Hong Kong SAR Department Of Electronic And Electrical Engineering Shenzhen Key Laboratory of Robotics Perception and Intelligence Southern University of Science and Technology Shenzhen China Noah's Ark Lab Huawei

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

Direct shooting is an efficient method to solve numerical optimal control. It utilizes the Runge-Kutta scheme to discretize a continuous-time optimal control problem making the problem solvable by nonlinear programming solvers. However, conventional direct shooting raises a contradictory dynamics issue when using an augmented state to handle high-order systems. This paper fills the research gap by considering the direct shooting method for high-order systems. We derive the modified Euler and Runge-Kutta-4 methods to transcribe the system dynamics constraint directly. Additionally, we provide the global error upper bounds of our proposed methods. A set of benchmark optimal control problems shows that our methods provide more accurate solutions than existing approaches.

关键词： Upper bound Accuracy System dynamics Optimal control Europe Programming Benchmark testing

Designing and Training of A Dual CNN for Image Denoising

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zuo, Wangmeng Zhang, David Lin, Chia-Wen Xu, Yong Tian, Chunwei Du, Bo Bio-Computing Research Center Harbin Institute of Technology Shenzhen China Shenzhen Key Laboratory of Visual Object Detection and Recognition ShenzhenGuangdong518055 China Peng Cheng Laboratory Shenzhen518055 China School of Computer Science and Technology Harbin Institute of Technology 150001 HarbinHeilongjiang China Peng Cheng Laboratory Shenzhen518055 China School of Computer Science Wuhan University 430072 WuhanHubei China Department of Electrical Engineering Institute of Communications Engineering National Tsing Hua University Hsinchu Taiwan 518172 ShenzhenGuangdong China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

Deep convolutional neural networks (CNNs) for image denoising have recently attracted increasing research interest. However, plain networks cannot recover fine details for a complex task, such as real noisy images. In this paper, we propose a Dual denoising Network (DudeNet) to recover a clean image. Specifically, DudeNet consists of four modules: a feature extraction block, an enhancement block, a compression block, and a reconstruction block. The feature extraction block with a sparse mechanism extracts global and local features via two sub-networks. The enhancement block gathers and fuses the global and local features to provide complementary information for the latter network. The compression block refines the extracted information and compresses the network. Finally, the reconstruction block is utilized to reconstruct a denoised image. The DudeNet has the following advantages: (1) The dual networks with a parse mechanism can extract complementary features to enhance the generalized ability of denoiser. (2) Fusing global and local features can extract salient features to recover fine details for complex noisy images. (3) A Small-size filter is used to reduce the complexity of denoiser. Extensive experiments demonstrate the superiority of DudeNet over existing current state-of-the-art denoising methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Recovery

Single shot text detector with regional attention

学校读者我要写书评

暂无评论

arXiv 2017年

作者： He, Pan Huang, Weilin He, Tong Zhu, Qile Qiao, Yu Li, Xiaolin National Science Foundation Center for Big Learning University of Florida Department of Engineering Science University of Oxford Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences

We present a novel single-shot text detector that directly outputs word-level bounding boxes in a natural image. We propose an attention mechanism which roughly identifies text regions via an automatically learned attentional map. This substantially suppresses background interference in the convolutional features, which is the key to producing accurate inference of words, particularly at extremely small sizes. This results in a single model that essentially works in a coarse-to-fine manner. It departs from recent FCN-based text detectors which cascade multiple FCN models to achieve an accurate prediction. Furthermore, we develop a hierarchical inception module which efficiently aggregates multi-scale inception features. This enhances local details, and also encodes strong context information, allowing the detector to work reliably on multi-scale and multi-orientation text with single-scale images. Our text detector achieves an F-measure of 77% on the ICDAR 2015 benchmark, advancing the state-of-the-art results in [18, 28]. Demo is available at: http://***/. Copyright © 2017, The Authors. All rights reserved.

关键词： Image enhancement

AO2-DETR: Arbitrary-Oriented Object Detection Transformer

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Dai, Linhui Liu, Hong Tang, Hao Wu, Zhiwei Song, Pinhao The Key Laboratory of Machine Perception Shenzhen Graduate School Peking University Beijing100871 China The Computer Vision Lab ETH Zurich Zurich Switzerland The School of Software Engineering South China University of Technology Guangdong Guangzhou China

Arbitrary-oriented object detection (AOOD) is a challenging task to detect objects in the wild with arbitrary orientations and cluttered arrangements. Existing approaches are mainly based on anchor-based boxes or dense points, which rely on complicated hand-designed processing steps and inductive bias, such as anchor generation, transformation, and non-maximum suppression reasoning. Recently, the emerging transformer-based approaches view object detection as a direct set prediction problem that effectively removes the need for handdesigned components and inductive biases. In this paper, we propose an Arbitrary-Oriented Object DEtection TRansformer framework, termed AO2-DETR, which comprises three dedicated components. More precisely, an oriented proposal generation mechanism is proposed to explicitly generate oriented proposals, which provides better positional priors for pooling features to modulate the cross-attention in the transformer decoder. An adaptive oriented proposal refinement module is introduced to extract rotation-invariant region features and eliminate the misalignment between region features and objects. And a rotationaware set matching loss is used to ensure the one-to-one matching process for direct set prediction without duplicate predictions. Our method considerably simplifies the overall pipeline and presents a new AOOD paradigm. Comprehensive experiments on several challenging datasets show that our method achieves superior performance on the AOOD task. Copyright © 2022, The Authors. All rights reserved.

关键词： Object recognition

Direction-aware spatial context features for shadow detection

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Hu, Xiaowei Zhu, Lei Fu, Chi-Wing Qin, Jing Heng, Pheng-Ann Department of Computer Science and Engineering Chinese University of Hong Kong Centre for Smart Health School of Nursing Hong Kong Polytechnic University Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China

Shadow detection is a fundamental and challenging task, since it requires an understanding of global image semantics and there are various backgrounds around shadows. This paper presents a novel network for shadow detection by analyzing image context in a direction-aware manner. To achieve this, we first formulate the direction-aware attention mechanism in a spatial recurrent neural network (RNN) by introducing attention weights when aggregating spatial context features in the RNN. By learning these weights through training, we can recover direction-aware spatial context (DSC) for detecting shadows. This design is developed into the DSC module and embedded in a CNN to learn DSC features at different levels. Moreover, a weighted cross entropy loss is designed to make the training more effective. We employ two common shadow detection benchmark datasets and perform various experiments to evaluate our network. Experimental results show that our network outperforms state-of-the-art methods and achieves 97% accuracy and 38% reduction on balance error rate. Copyright © 2017, The Authors. All rights reserved.

关键词： Recurrent neural networks