Attribute disentanglement and registration for occluded person re-identification

Shi, Yuxuan; Ling, Hefei; Wu, Lei; Zhang, Baiyan; Ping, Li

doi:10.1016/j.neucom.2021.11.013

Cited by 20 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, these methods significantly degrade when dealing with occluded images. While recent endeavors have facilitated person Re-ID under occlusion conditions [39,36,31,18,28,16], two main problems associated with occlusions still need to be addressed. Firstly, the presence of obstacles will vanish some parts of the human body, missing and misaligned extracted features.…”

Section: Introductionmentioning

confidence: 99%

Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-Identification

Xia¹,

Tan²,

Dai³

et al. 2023

Preprint

View full text Add to dashboard Cite

Occluded person re-identification (Re-ID) aims to address the potential occlusion problem when matching occluded or holistic pedestrians from different camera views. Many methods use the background as artificial occlusion and rely on attention networks to exclude noisy interference. However, the significant discrepancy between simple background occlusion and realistic occlusion can negatively impact the generalization of the network. To address this issue, we propose a novel transformer-based Attention Disturbance and Dual-Path Constraint Network (ADP) to enhance the generalization of attention networks. Firstly, to imitate real-world obstacles, we introduce an Attention Disturbance Mask (ADM) module that generates an offensive noise, which can distract attention like a realistic occluder, as a more complex form of occlusion. Secondly, to fully exploit these complex occluded images, we develop a Dual-Path Constraint Module (DPC) that can obtain preferable supervision information from holistic images through dualpath interaction. With our proposed method, the network can effectively circumvent a wide variety of occlusions using the basic ViT baseline. Comprehensive experimental evaluations conducted on person re-ID benchmarks demonstrate the superiority of ADP over state-of-the-art methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-Identification

Xia¹,

Tan²,

Dai³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, there have been preliminary explorations in addressing occluded ReID by some researches [15][16][17][18][19][20]. These…”

Section: Introductionmentioning

confidence: 99%

“…Recently, there have been preliminary explorations in addressing occluded ReID by some researches [15–20]. These methods typically focus on directing the attention of the backbone network towards the visible parts of pedestrian images or aligning only the visible parts of pedestrian images using pose estimation.…”

Section: Introductionmentioning

confidence: 99%

“…Consequently, pedestrian images with different types of occlusions often exhibit dislocations in image matching. While numerous existing approaches [5,[10][11][12][13][14] attempt to address these challenges by aligning the spatial features of body parts using external semantic cues or feature similarity, it should be noted that alignment approaches are complex and sensitive to noise, posing limitations on their effectiveness.Recently, there have been preliminary explorations in addressing occluded ReID by some researches [15][16][17][18][19][20]. TheseThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Anti‐occlusion person re‐identification via body topology information restoration and similarity evaluation

Meng,

Ganaa,

et al. 2023

IET Computer Vision

View full text Add to dashboard Cite

In real‐world scenarios, pedestrian images often suffer from occlusion, where certain body features become invisible, making it challenging for existing methods to accurately identify pedestrians with the same ID. Traditional approaches typically focus on matching only the visible body parts, which can lead to misalignment when the occlusion patterns vary. To address this issue and alleviate misalignment in occluded pedestrian images, the authors propose a novel framework called body topology information generation and matching. The framework consists of two main modules: the body topology information generation module and the body topology information matching module. The body topology information generation module employs an adaptive detection mechanism and capsule generative adversarial network to restore a holistic pedestrian image while preserving the body topology information. The body topology information matching module leverages the restored holistic image from body topology information generation to overcome spatial misalignment and utilises cosine distance as the similarity measure for matching. By combining the body topology information generation and body topology information matching modules, the authors achieve consistency in the body topology information features of pedestrian images, ranging from restoration to retrieval. Extensive experiments are conducted on both holistic person re‐identification datasets (Market‐1501, DukeMTMC‐ReID) and occluded person re‐identification datasets (Occluded‐DukeMTMC, Occluded‐ReID). The results demonstrate the superior performance of the authors proposed model, and visualisations of the generation and matching modules are provided to illustrate their effectiveness. Furthermore, an ablation study is conducted to validate the contributions of the proposed framework.

show abstract

“…The Thirty-Sixth AAAI Conference on Artificial Intelligence To handle noisy labels, some researchers use mutual teaching (Zhang et al 2018;Shi et al 2021) to train paired networks and help to correct each other. MMT trains two paired networks and corrects their pseudo labels by using their moving average networks.…”

Section: Introductionmentioning

confidence: 99%

Reliability Exploration with Self-Ensemble Learning for Domain Adaptive Person Re-identification

Shi

Ling

et al. 2022

AAAI

Self Cite

View full text Add to dashboard Cite

Person re-identifcation (Re-ID) based on unsupervised domain adaptation (UDA) aims to transfer the pre-trained model from one labeled source domain to an unlabeled target domain. Existing methods tackle this problem by using clustering methods to generate pseudo labels. However, pseudo labels produced by these techniques may be unstable and noisy, substantially deteriorating models’ performance. In this paper, we propose a Reliability Exploration with Self-ensemble Learning (RESL) framework for domain adaptive person ReID. First, to increase the feature diversity, multiple branches are presented to extract features from different data augmentations. Taking the temporally average model as a mean teacher model, online label refning is conducted by using its dynamic ensemble predictions from different branches as soft labels. Second, to combat the adverse effects of unreliable samples in clusters, sample reliability is estimated by evaluating the consistency of different clusters’ results, followed by selecting reliable instances for training and re-weighting sample contribution within Re-ID losses. A contrastive loss is also utilized with cluster-level memory features which are updated by the mean feature. The experiments demonstrate that our method can signifcantly surpass the state-of-the-art performance on the unsupervised domain adaptive person ReID.

show abstract

Attribute disentanglement and registration for occluded person re-identification

Cited by 20 publications

References 17 publications

Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-Identification

Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-Identification

Anti‐occlusion person re‐identification via body topology information restoration and similarity evaluation

Reliability Exploration with Self-Ensemble Learning for Domain Adaptive Person Re-identification

Contact Info

Product

Resources

About