Leaning Compact and Representative Features for Cross-Modality Person Re-Identification

• URL: http://arxiv.org/abs/2103.14210v1
• Date: Fri, 26 Mar 2021 01:53:16 GMT
• Title: Leaning Compact and Representative Features for Cross-Modality Person Re-Identification
• Authors: Guangwei Gao, Hao Shao, Yi Yu, Fei Wu, Meng Yang
• Abstract summary: This paper pays close attention to the cross-modality visible-infrared person re-identification (VI Re-ID) task. The proposed method is superior to the other most advanced methods in terms of impressive performance.
• Score: 18.06382007908855
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper pays close attention to the cross-modality visible-infrared person re-identification (VI Re-ID) task, which aims to match human samples between visible and infrared modes. In order to reduce the discrepancy between features of different modalities, most existing works usually use constraints based on Euclidean metric. Since the Euclidean based distance metric cannot effectively measure the internal angles between the embedded vectors, the above methods cannot learn the angularly discriminative feature embedding. Because the most important factor affecting the classification task based on embedding vector is whether there is an angularly discriminativ feature space, in this paper, we propose a new loss function called Enumerate Angular Triplet (EAT) loss. Also, motivated by the knowledge distillation, to narrow down the features between different modalities before feature embedding, we further present a new Cross-Modality Knowledge Distillation (CMKD) loss. The experimental results on RegDB and SYSU-MM01 datasets have shown that the proposed method is superior to the other most advanced methods in terms of impressive performance.

Related papers

• Sparse Prior Is Not All You Need: When Differential Directionality Meets Saliency Coherence for Infrared Small Target Detection [15.605122893098981]
  This study introduces a Sparse Differential Directionality prior (SDD) framework. We leverage the distinct directional characteristics of targets to differentiate them from the background. We further enhance target detectability with a saliency coherence strategy. A Proximal Alternating Minimization-based (PAM) algorithm efficiently solves our proposed model.
  arXiv  Detail & Related papers  (2024-07-22T04:32:43Z)
• Instance-Variant Loss with Gaussian RBF Kernel for 3D Cross-modal Retriveal [52.41252219453429]
  Existing methods treat all instances equally, applying the same penalty strength to instances with varying degrees of difficulty. This can result in ambiguous convergence or local optima, severely compromising the separability of the feature space. We propose an Instance-Variant loss to assign different penalty strengths to different instances, improving the space separability.
  arXiv  Detail & Related papers  (2023-05-07T10:12:14Z)
• DOAD: Decoupled One Stage Action Detection Network [77.14883592642782]
  Localizing people and recognizing their actions from videos is a challenging task towards high-level video understanding. Existing methods are mostly two-stage based, with one stage for person bounding box generation and the other stage for action recognition. We present a decoupled one-stage network dubbed DOAD, to improve the efficiency for-temporal action detection.
  arXiv  Detail & Related papers  (2023-04-01T08:06:43Z)
• MRCN: A Novel Modality Restitution and Compensation Network for Visible-Infrared Person Re-identification [36.88929785476334]
  We propose a novel Modality Restitution and Compensation Network (MRCN) to narrow the gap between the two modalities. Our method achieves 95.1% in terms of Rank-1 and 89.2% in terms of mAP on the RegDB dataset.
  arXiv  Detail & Related papers  (2023-03-26T05:03:18Z)
• Learning Progressive Modality-shared Transformers for Effective Visible-Infrared Person Re-identification [27.75907274034702]
  We propose a novel deep learning framework named Progressive Modality-shared Transformer (PMT) for effective VI-ReID. To reduce the negative effect of modality gaps, we first take the gray-scale images as an auxiliary modality and propose a progressive learning strategy. To cope with the problem of large intra-class differences and small inter-class differences, we propose a Discriminative Center Loss.
  arXiv  Detail & Related papers  (2022-12-01T02:20:16Z)
• CycleTrans: Learning Neutral yet Discriminative Features for Visible-Infrared Person Re-Identification [79.84912525821255]
  Visible-infrared person re-identification (VI-ReID) is a task of matching the same individuals across the visible and infrared modalities. Existing VI-ReID methods mainly focus on learning general features across modalities, often at the expense of feature discriminability. We present a novel cycle-construction-based network for neutral yet discriminative feature learning, termed CycleTrans.
  arXiv  Detail & Related papers  (2022-08-21T08:41:40Z)
• Benchmarking Deep Models for Salient Object Detection [67.07247772280212]
  We construct a general SALient Object Detection (SALOD) benchmark to conduct a comprehensive comparison among several representative SOD methods. In the above experiments, we find that existing loss functions usually specialized in some metrics but reported inferior results on the others. We propose a novel Edge-Aware (EA) loss that promotes deep networks to learn more discriminative features by integrating both pixel- and image-level supervision signals.
  arXiv  Detail & Related papers  (2022-02-07T03:43:16Z)
• On Exploring Pose Estimation as an Auxiliary Learning Task for Visible-Infrared Person Re-identification [66.58450185833479]
  In this paper, we exploit Pose Estimation as an auxiliary learning task to assist the VI-ReID task in an end-to-end framework. By jointly training these two tasks in a mutually beneficial manner, our model learns higher quality modality-shared and ID-related features. Experimental results on two benchmark VI-ReID datasets show that the proposed method consistently improves state-of-the-art methods by significant margins.
  arXiv  Detail & Related papers  (2022-01-11T09:44:00Z)
• MMD-ReID: A Simple but Effective Solution for Visible-Thermal Person ReID [20.08880264104061]
  We propose a simple but effective framework, MMD-ReID, that reduces the modality gap by an explicit discrepancy reduction constraint. We conduct extensive experiments to demonstrate both qualitatively and quantitatively the effectiveness of MMD-ReID. The proposed framework significantly outperforms the state-of-the-art methods on SYSU-MM01 and RegDB datasets.
  arXiv  Detail & Related papers  (2021-11-09T11:33:32Z)
• Meta Learning Low Rank Covariance Factors for Energy-Based Deterministic Uncertainty [58.144520501201995]
  Bi-Lipschitz regularization of neural network layers preserve relative distances between data instances in the feature spaces of each layer. With the use of an attentive set encoder, we propose to meta learn either diagonal or diagonal plus low-rank factors to efficiently construct task specific covariance matrices. We also propose an inference procedure which utilizes scaled energy to achieve a final predictive distribution.
  arXiv  Detail & Related papers  (2021-10-12T22:04:19Z)
• Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification [18.09586167227815]
  We propose a novel ranking loss function, named Bi-directional Exponential Angular Triplet Loss, to help learn an angularly separable common feature space. On SYSU-MM01 dataset, the performance is improved from 7.40% / 11.46% to 38.57% / 38.61% for rank-1 accuracy / mAP. The proposed method can be generalized to the task of single-modality Re-ID.
  arXiv  Detail & Related papers  (2020-06-01T12:26:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.