Occlusion-Guided Feature Purification Learning via Reinforced Knowledge Distillation for Occluded Person Re-Identification

• URL: http://arxiv.org/abs/2507.08520v1
• Date: Fri, 11 Jul 2025 12:05:30 GMT
• Title: Occlusion-Guided Feature Purification Learning via Reinforced Knowledge Distillation for Occluded Person Re-Identification
• Authors: Yufei Zheng, Wenjun Wang, Wenjun Gan, Jiawei Liu,
• Abstract summary: Occluded person re-identification aims to retrieve holistic images based on occluded ones.<n>Existing methods often rely on aligning visible body parts, applying occlusion augmentation, or complementing missing semantics.<n>We propose Occlusion-Guided Feature Purification Learning via Reinforced Knowledge Distillation.
• Score: 5.193166724401499
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Occluded person re-identification aims to retrieve holistic images based on occluded ones. Existing methods often rely on aligning visible body parts, applying occlusion augmentation, or complementing missing semantics using holistic images. However, they face challenges in handling diverse occlusion scenarios not seen during training and the issue of feature contamination from holistic images. To address these limitations, we propose Occlusion-Guided Feature Purification Learning via Reinforced Knowledge Distillation (OGFR), which simultaneously mitigates these challenges. OGFR adopts a teacher-student distillation architecture that effectively incorporates diverse occlusion patterns into feature representation while transferring the purified discriminative holistic knowledge from the holistic to the occluded branch through reinforced knowledge distillation. Specifically, an Occlusion-Aware Vision Transformer is designed to leverage learnable occlusion pattern embeddings to explicitly model such diverse occlusion types, thereby guiding occlusion-aware robust feature representation. Moreover, we devise a Feature Erasing and Purification Module within the holistic branch, in which an agent is employed to identify low-quality patch tokens of holistic images that contain noisy negative information via deep reinforcement learning, and substitute these patch tokens with learnable embedding tokens to avoid feature contamination and further excavate identity-related discriminative clues. Afterward, with the assistance of knowledge distillation, the student branch effectively absorbs the purified holistic knowledge to precisely learn robust representation regardless of the interference of occlusions.

Related papers

• Mind the Gap: Bridging Occlusion in Gait Recognition via Residual Gap Correction [57.75544235445363]
  We propose RG-Gait, a method for residual correction for occluded gait recognition with holistic retention.<n>Our proposed network adaptively integrates the learned residual, significantly improving performance on occluded gait sequences.
  arXiv  Detail & Related papers  (2025-07-15T04:45:14Z)
• Improving Apple Object Detection with Occlusion-Enhanced Distillation [1.0049237739132246]
  Apples growing in natural environments often face severe visual obstructions from leaves and branches. We introduce a technique called "Occlusion-Enhanced Distillation" (OED) to regularize the learning of semantically aligned features on occluded datasets. Our method significantly outperforms current state-of-the-art techniques through extensive comparative experiments.
  arXiv  Detail & Related papers  (2024-09-03T03:11:48Z)
• You Can Run but not Hide: Improving Gait Recognition with Intrinsic Occlusion Type Awareness [48.151855620080134]
  Occluded body parts can affect gait recognition from uncontrolled outdoor sequences at range. Most current methods assume the availability of complete body information while extracting the gait features. We propose an occlusion aware gait recognition method which can be used to model intrinsic occlusion awareness into potentially any state-of-the-art gait recognition method.
  arXiv  Detail & Related papers  (2023-12-04T19:11:40Z)
• Free-ATM: Exploring Unsupervised Learning on Diffusion-Generated Images with Free Attention Masks [64.67735676127208]
  Text-to-image diffusion models have shown great potential for benefiting image recognition. Although promising, there has been inadequate exploration dedicated to unsupervised learning on diffusion-generated images. We introduce customized solutions by fully exploiting the aforementioned free attention masks.
  arXiv  Detail & Related papers  (2023-08-13T10:07:46Z)
• Feature Completion Transformer for Occluded Person Re-identification [25.159974510754992]
  Occluded person re-identification (Re-ID) is a challenging problem due to the destruction of occluders. We propose a Feature Completion Transformer (FCFormer) to implicitly complement the semantic information of occluded parts in the feature space. FCFormer achieves superior performance and outperforms the state-of-the-art methods by significant margins on occluded datasets.
  arXiv  Detail & Related papers  (2023-03-03T01:12:57Z)
• Towards Intrinsic Common Discriminative Features Learning for Face Forgery Detection using Adversarial Learning [59.548960057358435]
  We propose a novel method which utilizes adversarial learning to eliminate the negative effect of different forgery methods and facial identities. Our face forgery detection model learns to extract common discriminative features through eliminating the effect of forgery methods and facial identities.
  arXiv  Detail & Related papers  (2022-07-08T09:23:59Z)
• Open-set Adversarial Defense with Clean-Adversarial Mutual Learning [93.25058425356694]
  This paper demonstrates that open-set recognition systems are vulnerable to adversarial samples. Motivated by these observations, we emphasize the necessity of an Open-Set Adversarial Defense (OSAD) mechanism. This paper proposes an Open-Set Defense Network with Clean-Adversarial Mutual Learning (OSDN-CAML) as a solution to the OSAD problem.
  arXiv  Detail & Related papers  (2022-02-12T02:13:55Z)
• Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification [137.8810152620818]
  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.
  arXiv  Detail & Related papers  (2021-07-31T03:34:27Z)
• Locality-aware Channel-wise Dropout for Occluded Face Recognition [116.2355331029041]
  Face recognition is a challenging task in unconstrained scenarios, especially when faces are partially occluded. We propose a novel and elegant occlusion-simulation method via dropping the activations of a group of neurons in some elaborately selected channel. Experiments on various benchmarks show that the proposed method outperforms state-of-the-art methods with a remarkable improvement.
  arXiv  Detail & Related papers  (2021-07-20T05:53:14Z)
• Transformer with Peak Suppression and Knowledge Guidance for Fine-grained Image Recognition [24.02553270481428]
  We propose a transformer architecture with the peak suppression module and knowledge guidance module. The peak suppression module penalizes the attention to the most discriminative parts in the feature learning process. The knowledge guidance module compares the image-based representation generated from the peak suppression module with the learnable knowledge embedding set to obtain the knowledge response coefficients.
  arXiv  Detail & Related papers  (2021-07-14T08:07:58Z)

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.