AAformer: Auto-Aligned Transformer for Person Re-Identification

• URL: http://arxiv.org/abs/2104.00921v3
• Date: Tue, 25 Jun 2024 04:08:21 GMT
• Title: AAformer: Auto-Aligned Transformer for Person Re-Identification
• Authors: Kuan Zhu, Haiyun Guo, Shiliang Zhang, Yaowei Wang, Jing Liu, Jinqiao Wang, Ming Tang,
• Abstract summary: We introduce an alignment scheme in transformer architecture for the first time. We propose the auto-aligned transformer (AAformer) to automatically locate both the human parts and nonhuman ones at patch level. AAformer integrates the part alignment into the self-attention and the output [PART]s can be directly used as part features for retrieval.
• Score: 82.45385078624301
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In person re-identification (re-ID), extracting part-level features from person images has been verified to be crucial to offer fine-grained information. Most of the existing CNN-based methods only locate the human parts coarsely, or rely on pretrained human parsing models and fail in locating the identifiable nonhuman parts (e.g., knapsack). In this article, we introduce an alignment scheme in transformer architecture for the first time and propose the auto-aligned transformer (AAformer) to automatically locate both the human parts and nonhuman ones at patch level. We introduce the "Part tokens ([PART]s)", which are learnable vectors, to extract part features in the transformer. A [PART] only interacts with a local subset of patches in self-attention and learns to be the part representation. To adaptively group the image patches into different subsets, we design the auto-alignment. Auto-alignment employs a fast variant of optimal transport (OT) algorithm to online cluster the patch embeddings into several groups with the [PART]s as their prototypes. AAformer integrates the part alignment into the self-attention and the output [PART]s can be directly used as part features for retrieval. Extensive experiments validate the effectiveness of [PART]s and the superiority of AAformer over various state-of-the-art methods.

Related papers

• PAFormer: Part Aware Transformer for Person Re-identification [3.8004980982852214]
  We introduce textbfPart Aware Transformer (PAFormer), a pose estimation based ReID model which can perform precise part-to-part comparison. Our method outperforms existing approaches on well-known ReID benchmark datasets.
  arXiv  Detail & Related papers  (2024-08-12T04:46:55Z)
• A Transformer-Based Adaptive Semantic Aggregation Method for UAV Visual Geo-Localization [2.1462492411694756]
  This paper addresses the task of Unmanned Aerial Vehicles (UAV) visual geo-localization. Part matching is crucial for UAV visual geo-localization since part-level representations can capture image details and help to understand the semantic information of scenes. We introduce a transformer-based adaptive semantic aggregation method that regards parts as the most representative semantics in an image.
  arXiv  Detail & Related papers  (2024-01-03T06:58:52Z)
• PDiscoNet: Semantically consistent part discovery for fine-grained recognition [62.12602920807109]
  We propose PDiscoNet to discover object parts by using only image-level class labels along with priors encouraging the parts to be. Our results on CUB, CelebA, and PartImageNet show that the proposed method provides substantially better part discovery performance than previous methods.
  arXiv  Detail & Related papers  (2023-09-06T17:19:29Z)
• ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection [20.983998911754792]
  Two-stage Human-Object Interaction (HOI) detectors suffer from lower performance than one-stage methods. We propose Vision Transformer based Pose-Conditioned Self-Loop Graph (ViPLO) to resolve these problems. ViPLO achieves the state-of-the-art results on two public benchmarks.
  arXiv  Detail & Related papers  (2023-04-17T09:44:54Z)
• MOST: Multiple Object localization with Self-supervised Transformers for object discovery [97.47075050779085]
  We present Multiple Object localization with Self-supervised Transformers (MOST) MOST uses features of transformers trained using self-supervised learning to localize multiple objects in real world images. We show MOST can be used for self-supervised pre-training of object detectors, and yields consistent improvements on fully, semi-supervised object detection and unsupervised region proposal generation.
  arXiv  Detail & Related papers  (2023-04-11T17:57:27Z)
• Part-guided Relational Transformers for Fine-grained Visual Recognition [59.20531172172135]
  We propose a framework to learn the discriminative part features and explore correlations with a feature transformation module. Our proposed approach does not rely on additional part branches and reaches state-the-of-art performance on 3-of-the-level object recognition.
  arXiv  Detail & Related papers  (2022-12-28T03:45:56Z)
• 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)
• Short Range Correlation Transformer for Occluded Person Re-Identification [4.339510167603376]
  We propose a partial feature transformer-based person re-identification framework named PFT. The proposed PFT utilizes three modules to enhance the efficiency of vision transformer. Experimental results over occluded and holistic re-identification datasets demonstrate that the proposed PFT network achieves superior performance consistently.
  arXiv  Detail & Related papers  (2022-01-04T11:12:39Z)
• PnP-DETR: Towards Efficient Visual Analysis with Transformers [146.55679348493587]
  Recently, DETR pioneered the solution vision tasks with transformers, it directly translates the image feature map into the object result. Recent transformer-based image recognition model andTT show consistent efficiency gain.
  arXiv  Detail & Related papers  (2021-09-15T01:10:30Z)

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.