DiP: Learning Discriminative Implicit Parts for Person Re-Identification
- URL: http://arxiv.org/abs/2212.13906v1
- Date: Sat, 24 Dec 2022 17:59:01 GMT
- Title: DiP: Learning Discriminative Implicit Parts for Person Re-Identification
- Authors: Dengjie Li, Siyu Chen, Yujie Zhong, Fan Liang, Lin Ma
- Abstract summary: We propose to learn Discriminative implicit Parts (DiPs) which are decoupled from explicit body parts.
We also propose a novel implicit position to give a geometric interpretation for each DiP.
The proposed method achieves state-of-the-art performance on multiple person ReID benchmarks.
- Score: 18.89539401924382
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In person re-identification (ReID) tasks, many works explore the learning of
part features to improve the performance over global image features. Existing
methods extract part features in an explicit manner, by either using a
hand-designed image division or keypoints obtained with external visual
systems. In this work, we propose to learn Discriminative implicit Parts (DiPs)
which are decoupled from explicit body parts. Therefore, DiPs can learn to
extract any discriminative features that can benefit in distinguishing
identities, which is beyond predefined body parts (such as accessories).
Moreover, we propose a novel implicit position to give a geometric
interpretation for each DiP. The implicit position can also serve as a learning
signal to encourage DiPs to be more position-equivariant with the identity in
the image. Lastly, a set of attributes and auxiliary losses are introduced to
further improve the learning of DiPs. Extensive experiments show that the
proposed method achieves state-of-the-art performance on multiple person ReID
benchmarks.
Related papers
- Unsupervised Part Discovery via Dual Representation Alignment [31.100169532078095]
Object parts serve as crucial intermediate representations in various downstream tasks.
Previous research has established that Vision Transformer can learn instance-level attention without labels.
In this paper, we achieve unsupervised part-specific attention learning using a novel paradigm.
arXiv Detail & Related papers (2024-08-15T12:11:20Z) - 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 Transferable Pedestrian Representation from Multimodal
Information Supervision [174.5150760804929]
VAL-PAT is a novel framework that learns transferable representations to enhance various pedestrian analysis tasks with multimodal information.
We first perform pre-training on LUPerson-TA dataset, where each image contains text and attribute annotations.
We then transfer the learned representations to various downstream tasks, including person reID, person attribute recognition and text-based person search.
arXiv Detail & Related papers (2023-04-12T01:20:58Z) - 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) - 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) - Dynamic Template Initialization for Part-Aware Person Re-ID [0.640781528166787]
spatial attention-based Dynamic Part template Initialization module.
Part-level features of the backbone are used to extract the templates of diverse human body parts.
Tests on holistic, occluded, and partial Re-ID task benchmarks.
arXiv Detail & Related papers (2022-08-24T11:20:48Z) - An Empirical Investigation of Representation Learning for Imitation [76.48784376425911]
Recent work in vision, reinforcement learning, and NLP has shown that auxiliary representation learning objectives can reduce the need for large amounts of expensive, task-specific data.
We propose a modular framework for constructing representation learning algorithms, then use our framework to evaluate the utility of representation learning for imitation.
arXiv Detail & Related papers (2022-05-16T11:23:42Z) - PGGANet: Pose Guided Graph Attention Network for Person
Re-identification [0.0]
Person re-identification (ReID) aims at retrieving a person from images captured by different cameras.
It has been proved that using local features together with global feature of person image could help to give robust feature representations for person retrieval.
We propose a pose guided graph attention network, a multi-branch architecture consisting of one branch for global feature, one branch for mid-granular body features and one branch for fine-granular key point features.
arXiv Detail & Related papers (2021-11-29T09:47:39Z) - 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) - 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)
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.