Multi-Level Attention for Unsupervised Person Re-Identification

• URL: http://arxiv.org/abs/2201.03141v1
• Date: Mon, 10 Jan 2022 02:47:06 GMT
• Title: Multi-Level Attention for Unsupervised Person Re-Identification
• Authors: Yi Zheng
• Abstract summary: In unsupervised person re-identification, the attention module represented by multi-headed self-attention suffers from attention spreading in the condition of non-ground truth. We design pixel-level attention module to provide constraints for multi-headed self-attention. For the trait that the identification targets of person re-identification data are all pedestrians, we design domain-level attention module.
• Score: 9.529435737056179
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The attention mechanism is widely used in deep learning because of its excellent performance in neural networks without introducing additional information. However, in unsupervised person re-identification, the attention module represented by multi-headed self-attention suffers from attention spreading in the condition of non-ground truth. To solve this problem, we design pixel-level attention module to provide constraints for multi-headed self-attention. Meanwhile, for the trait that the identification targets of person re-identification data are all pedestrians in the samples, we design domain-level attention module to provide more comprehensive pedestrian features. We combine head-level, pixel-level and domain-level attention to propose multi-level attention block and validate its performance on for large person re-identification datasets (Market-1501, DukeMTMC-reID and MSMT17 and PersonX).

Related papers

• Spectrum-guided Feature Enhancement Network for Event Person Re-Identification [82.52960675574353]
  We introduce the Spectrum-guided Feature Enhancement Network (SFE-Net) The SFE-Net consists of two innovative components: the Multi-grain Spectrum Attention Mechanism (MSAM) and the Consecutive Patch Dropout Module (CPDM)
  arXiv  Detail & Related papers  (2024-02-02T09:47:26Z)
• Learning Cross-modality Information Bottleneck Representation for Heterogeneous Person Re-Identification [61.49219876388174]
  Visible-Infrared person re-identification (VI-ReID) is an important and challenging task in intelligent video surveillance. Existing methods mainly focus on learning a shared feature space to reduce the modality discrepancy between visible and infrared modalities. We present a novel mutual information and modality consensus network, namely CMInfoNet, to extract modality-invariant identity features.
  arXiv  Detail & Related papers  (2023-08-29T06:55:42Z)
• Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification [19.957957963417414]
  We propose a dual cross-attention learning (DCAL) algorithm to coordinate with self-attention learning. First, we propose global-local cross-attention (GLCA) to enhance the interactions between global images and local high-response regions. Second, we propose pair-wise cross-attention (PWCA) to establish the interactions between image pairs.
  arXiv  Detail & Related papers  (2022-05-04T16:14:26Z)
• Alignment Attention by Matching Key and Query Distributions [48.93793773929006]
  This paper introduces alignment attention that explicitly encourages self-attention to match the distributions of the key and query within each head. It is simple to convert any models with self-attention, including pre-trained ones, to the proposed alignment attention. On a variety of language understanding tasks, we show the effectiveness of our method in accuracy, uncertainty estimation, generalization across domains, and robustness to adversarial attacks.
  arXiv  Detail & Related papers  (2021-10-25T00:54:57Z)
• Person Re-identification via Attention Pyramid [74.80544921378998]
  We propose an attention pyramid method for person re-identification. Our attention pyramid exploits the attention regions in a multi-scale manner because human attention varies with different scales. We evaluate our method on four largescale person re-identification benchmarks including Market-1501, DukeMTMC, CUHK03, and MSMT17.
  arXiv  Detail & Related papers  (2021-08-11T17:33:36Z)
• Information Bottleneck Approach to Spatial Attention Learning [21.083618550304703]
  The selective visual attention mechanism in the human visual system (HVS) restricts the amount of information to reach visual awareness for perceiving natural scenes. This kind of selectivity acts as an 'Information Bottleneck (IB)', which seeks a trade-off between information compression and predictive accuracy. We propose an IB-inspired spatial attention module for deep neural networks (DNNs) built for visual recognition.
  arXiv  Detail & Related papers  (2021-08-07T10:35:32Z)
• Multi-Branch with Attention Network for Hand-Based Person Recognition [5.162308830328819]
  We propose a novel hand-based person recognition method for the purpose of criminal investigations. Our proposed method, Multi-Branch with Attention Network (MBA-Net), incorporates both channel and spatial attention modules. Our proposed method achieves state-of-the-art performance, surpassing the existing hand-based identification methods.
  arXiv  Detail & Related papers  (2021-08-04T18:25:08Z)
• Deep Reinforced Attention Learning for Quality-Aware Visual Recognition [73.15276998621582]
  We build upon the weakly-supervised generation mechanism of intermediate attention maps in any convolutional neural networks. We introduce a meta critic network to evaluate the quality of attention maps in the main network.
  arXiv  Detail & Related papers  (2020-07-13T02:44:38Z)
• Deep Attention Aware Feature Learning for Person Re-Identification [22.107332426681072]
  We propose to incorporate the attention learning as additional objectives in a person ReID network without changing the original structure. We have tested its performance on two typical networks (TriNet and Bag of Tricks) and observed significant performance improvement on five widely used datasets.
  arXiv  Detail & Related papers  (2020-03-01T16:27:14Z)
• Intra-Camera Supervised Person Re-Identification [87.88852321309433]
  We propose a novel person re-identification paradigm based on an idea of independent per-camera identity annotation. This eliminates the most time-consuming and tedious inter-camera identity labelling process. We formulate a Multi-tAsk mulTi-labEl (MATE) deep learning method for Intra-Camera Supervised (ICS) person re-id.
  arXiv  Detail & Related papers  (2020-02-12T15:26:33Z)

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.