Feature Completion Transformer for Occluded Person Re-identification

• URL: http://arxiv.org/abs/2303.01656v2
• Date: Sat, 23 Mar 2024 07:45:14 GMT
• Title: Feature Completion Transformer for Occluded Person Re-identification
• Authors: Tao Wang, Mengyuan Liu, Hong Liu, Wenhao Li, Miaoju Ban, Tuanyu Guo, Yidi Li,
• Abstract summary: 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.
• Score: 25.159974510754992
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Occluded person re-identification (Re-ID) is a challenging problem due to the destruction of occluders. Most existing methods focus on visible human body parts through some prior information. However, when complementary occlusions occur, features in occluded regions can interfere with matching, which affects performance severely. In this paper, different from most previous works that discard the occluded region, we propose a Feature Completion Transformer (FCFormer) to implicitly complement the semantic information of occluded parts in the feature space. Specifically, Occlusion Instance Augmentation (OIA) is proposed to simulates real and diverse occlusion situations on the holistic image. These augmented images not only enrich the amount of occlusion samples in the training set, but also form pairs with the holistic images. Subsequently, a dual-stream architecture with a shared encoder is proposed to learn paired discriminative features from pairs of inputs. Without additional semantic information, an occluded-holistic feature sample-label pair can be automatically created. Then, Feature Completion Decoder (FCD) is designed to complement the features of occluded regions by using learnable tokens to aggregate possible information from self-generated occluded features. Finally, we propose the Cross Hard Triplet (CHT) loss to further bridge the gap between complementing features and extracting features under the same ID. In addition, Feature Completion Consistency (FC$^2$) loss is introduced to help the generated completion feature distribution to be closer to the real holistic feature distribution. Extensive experiments over five challenging datasets demonstrate that the proposed FCFormer achieves superior performance and outperforms the state-of-the-art methods by significant margins on occluded datasets.

Related papers

• Imagine the Unseen: Occluded Pedestrian Detection via Adversarial Feature Completion [31.488897675973657]
  We propose to complete features for occluded regions so as to align the features of pedestrians across different occlusion patterns. In order to narrow down the gap between completed features and real fully visible ones, we propose an adversarial learning method. We report experimental results on the CityPersons, Caltech and CrowdHuman datasets.
  arXiv  Detail & Related papers  (2024-05-02T14:20:20Z)
• Robust Ensemble Person Re-Identification via Orthogonal Fusion with Occlusion Handling [4.431087385310259]
  Occlusion remains one of the major challenges in person reidentification (ReID) We propose a deep ensemble model that harnesses both CNN and Transformer architectures to generate robust feature representations.
  arXiv  Detail & Related papers  (2024-03-29T18:38:59Z)
• Exploring Fine-Grained Representation and Recomposition for Cloth-Changing Person Re-Identification [78.52704557647438]
  We propose a novel FIne-grained Representation and Recomposition (FIRe$2$) framework to tackle both limitations without any auxiliary annotation or data. Experiments demonstrate that FIRe$2$ can achieve state-of-the-art performance on five widely-used cloth-changing person Re-ID benchmarks.
  arXiv  Detail & Related papers  (2023-08-21T12:59:48Z)
• Learning Feature Recovery Transformer for Occluded Person Re-identification [71.18476220969647]
  We propose a new approach called Feature Recovery Transformer (FRT) to address the two challenges simultaneously. To reduce the interference of the noise during feature matching, we mainly focus on visible regions that appear in both images and develop a visibility graph to calculate the similarity. In terms of the second challenge, based on the developed graph similarity, for each query image, we propose a recovery transformer that exploits the feature sets of its $k$-nearest neighbors in the gallery to recover the complete features.
  arXiv  Detail & Related papers  (2023-01-05T02:36:16Z)
• Dynamic Feature Pruning and Consolidation for Occluded Person Re-Identification [21.006680330530852]
  We propose a feature pruning and consolidation (FPC) framework to circumvent explicit human structure parsing. The framework mainly consists of a sparse encoder, a multi-view feature mathcing module, and a feature consolidation decoder. Our method outperforms state-of-the-art results by at least 8.6% mAP and 6.0% Rank-1 accuracy on the challenging Occluded-Duke dataset.
  arXiv  Detail & Related papers  (2022-11-27T06:18:40Z)
• Dynamic Prototype Mask for Occluded Person Re-Identification [88.7782299372656]
  Existing methods mainly address this issue by employing body clues provided by an extra network to distinguish the visible part. We propose a novel Dynamic Prototype Mask (DPM) based on two self-evident prior knowledge. Under this condition, the occluded representation could be well aligned in a selected subspace spontaneously.
  arXiv  Detail & Related papers  (2022-07-19T03:31:13Z)
• Generative Partial Visual-Tactile Fused Object Clustering [81.17645983141773]
  We propose a Generative Partial Visual-Tactile Fused (i.e., GPVTF) framework for object clustering. A conditional cross-modal clustering generative adversarial network is then developed to synthesize one modality conditioning on the other modality. To the end, two pseudo-label based KL-divergence losses are employed to update the corresponding modality-specific encoders.
  arXiv  Detail & Related papers  (2020-12-28T02:37:03Z)
• AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild [77.43884383743872]
  We present AdaFuse, an adaptive multiview fusion method to enhance the features in occluded views. We extensively evaluate the approach on three public datasets including Human3.6M, Total Capture and CMU Panoptic. We also create a large scale synthetic dataset Occlusion-Person, which allows us to perform numerical evaluation on the occluded joints.
  arXiv  Detail & Related papers  (2020-10-26T03:19:46Z)
• 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.