Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification

• URL: http://arxiv.org/abs/2108.00139v1
• Date: Sat, 31 Jul 2021 03:34:27 GMT
• Title: Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification
• Authors: Kecheng Zheng, Cuiling Lan, Wenjun Zeng, Jiawei Liu, Zhizheng Zhang, Zheng-Jun Zha
• Abstract summary: We propose a network named Pose-Guided Feature Learning with Knowledge Distillation (PGFL-KD) The PGFL-KD consists of a main branch (MB), and two pose-guided branches, ieno, a foreground-enhanced branch (FEB), and a body part semantics aligned branch (SAB) Experiments on occluded, partial, and holistic ReID tasks show the effectiveness of our proposed network.
• Score: 137.8810152620818
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Occluded person re-identification (ReID) aims to match person images with occlusion. It is fundamentally challenging because of the serious occlusion which aggravates the misalignment problem between images. At the cost of incorporating a pose estimator, many works introduce pose information to alleviate the misalignment in both training and testing. To achieve high accuracy while preserving low inference complexity, we propose a network named Pose-Guided Feature Learning with Knowledge Distillation (PGFL-KD), where the pose information is exploited to regularize the learning of semantics aligned features but is discarded in testing. PGFL-KD consists of a main branch (MB), and two pose-guided branches, \ieno, a foreground-enhanced branch (FEB), and a body part semantics aligned branch (SAB). The FEB intends to emphasise the features of visible body parts while excluding the interference of obstructions and background (\ieno, foreground feature alignment). The SAB encourages different channel groups to focus on different body parts to have body part semantics aligned representation. To get rid of the dependency on pose information when testing, we regularize the MB to learn the merits of the FEB and SAB through knowledge distillation and interaction-based training. Extensive experiments on occluded, partial, and holistic ReID tasks show the effectiveness of our proposed network.

Related papers

• Shape-Erased Feature Learning for Visible-Infrared Person Re-Identification [90.39454748065558]
  Body shape is one of the significant modality-shared cues for VI-ReID. We propose shape-erased feature learning paradigm that decorrelates modality-shared features in two subspaces. Experiments on SYSU-MM01, RegDB, and HITSZ-VCM datasets demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2023-04-09T10:22:10Z)
• Occluded Person Re-Identification via Relational Adaptive Feature Correction Learning [8.015703163954639]
  Occluded person re-identification (Re-ID) in images captured by multiple cameras is challenging because the target person is occluded by pedestrians or objects. Most existing methods utilize the off-the-shelf pose or parsing networks as pseudo labels, which are prone to error. We propose a novel Occlusion Correction Network (OCNet) that corrects features through relational-weight learning and obtains diverse and representative features without using external networks.
  arXiv  Detail & Related papers  (2022-12-09T07:48:47Z)
• Pose-disentangled Contrastive Learning for Self-supervised Facial Representation [12.677909048435408]
  We propose a novel Pose-disentangled Contrastive Learning (PCL) method for general self-supervised facial representation. Our PCL first devises a pose-disentangled decoder (PDD), which disentangles the pose-related features from the face-aware features. We then introduce a pose-related contrastive learning scheme that learns pose-related information based on data augmentation of the same image.
  arXiv  Detail & Related papers  (2022-11-24T09:30:51Z)
• Body Part-Based Representation Learning for Occluded Person Re-Identification [102.27216744301356]
  Occluded person re-identification (ReID) is a person retrieval task which aims at matching occluded person images with holistic ones. Part-based methods have been shown beneficial as they offer fine-grained information and are well suited to represent partially visible human bodies. We propose BPBreID, a body part-based ReID model for solving the above issues.
  arXiv  Detail & Related papers  (2022-11-07T16:48:41Z)
• Pose Attention-Guided Profile-to-Frontal Face Recognition [13.96448286983864]
  We propose a new approach to utilize pose as an auxiliary information via an attention mechanism. We develop a novel pose attention block (PAB) to specially guide the pose-agnostic feature extraction from profile faces. To be more specific, PAB is designed to explicitly help the network to focus on important features along both channel and spatial dimension.
  arXiv  Detail & Related papers  (2022-09-15T02:06:31Z)
• Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer [15.839842504357144]
  Occluded person re-identification is a challenging task as human body parts could be occluded by some obstacles. Some existing pose-guided methods solve this problem by aligning body parts according to graph matching. We propose a transformer-based Pose-guided Feature Disentangling (PFD) method by utilizing pose information to clearly disentangle semantic components.
  arXiv  Detail & Related papers  (2021-12-05T03:23:31Z)
• Batch Coherence-Driven Network for Part-aware Person Re-Identification [79.33809815035127]
  Existing part-aware person re-identification methods typically employ two separate steps: namely, body part detection and part-level feature extraction. We propose NetworkBCDNet that bypasses body part during both the training and testing phases while still semantically aligned features.
  arXiv  Detail & Related papers  (2020-09-21T09:04:13Z)
• Pose-guided Visible Part Matching for Occluded Person ReID [80.81748252960843]
  We propose a Pose-guided Visible Part Matching (PVPM) method that jointly learns the discriminative features with pose-guided attention and self-mines the part visibility. Experimental results on three reported occluded benchmarks show that the proposed method achieves competitive performance to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-04-01T04:36:51Z)
• High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification [84.43394420267794]
  We propose a novel framework by learning high-order relation and topology information for discriminative features and robust alignment. Our framework significantly outperforms state-of-the-art by6.5%mAP scores on Occluded-Duke dataset.
  arXiv  Detail & Related papers  (2020-03-18T12:18:35Z)

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.