Making Person Search Enjoy the Merits of Person Re-identification

• URL: http://arxiv.org/abs/2108.10536v1
• Date: Tue, 24 Aug 2021 06:00:13 GMT
• Title: Making Person Search Enjoy the Merits of Person Re-identification
• Authors: Chuang Liu, Hua Yang, Qin Zhou and Shibao Zheng
• Abstract summary: We propose a faster and stronger one-step person search framework, the Teacher-guided Disentangling Networks (TDN) The proposed TDN can significantly boost the person search performance by transferring the advanced person Re-ID knowledge to the person search model. We also propose a Knowledge Transfer Bridge module to bridge the scale gap caused by different input formats between the Re-ID model and one-step person search model.
• Score: 12.311100923753449
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Person search is an extended task of person re-identification (Re-ID). However, most existing one-step person search works have not studied how to employ existing advanced Re-ID models to boost the one-step person search performance due to the integration of person detection and Re-ID. To address this issue, we propose a faster and stronger one-step person search framework, the Teacher-guided Disentangling Networks (TDN), to make the one-step person search enjoy the merits of the existing Re-ID researches. The proposed TDN can significantly boost the person search performance by transferring the advanced person Re-ID knowledge to the person search model. In the proposed TDN, for better knowledge transfer from the Re-ID teacher model to the one-step person search model, we design a strong one-step person search base framework by partially disentangling the two subtasks. Besides, we propose a Knowledge Transfer Bridge module to bridge the scale gap caused by different input formats between the Re-ID model and one-step person search model. During testing, we further propose the Ranking with Context Persons strategy to exploit the context information in panoramic images for better retrieval. Experiments on two public person search datasets demonstrate the favorable performance of the proposed method.

Related papers

• Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training [51.87027943520492]
  We present a novel paradigm Diffusion-ReID to efficiently augment and generate diverse images based on known identities. Benefiting from our proposed paradigm, we first create a new large-scale person Re-ID dataset Diff-Person, which consists of over 777K images from 5,183 identities.
  arXiv  Detail & Related papers  (2024-06-10T06:26:03Z)
• Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search [60.626459715780605]
  Given a descriptive text query, text-based person search aims to retrieve the best-matched target person from an image gallery. Such a cross-modal retrieval task is quite challenging due to significant modality gap, fine-grained differences and insufficiency of annotated data. In this paper, we propose a simple yet effective dual Transformer model for text-based person search.
  arXiv  Detail & Related papers  (2023-11-15T16:26:49Z)
• PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement [59.6260680005195]
  We present a novel Person Search framework based on the Diffusion model, PSDiff. PSDiff formulates the person search as a dual denoising process from noisy boxes and ReID embeddings to ground truths. Following the new paradigm, we further design a new Collaborative Denoising Layer (CDL) to optimize detection and ReID sub-tasks in an iterative and collaborative way.
  arXiv  Detail & Related papers  (2023-09-20T08:16:39Z)
• Towards Fully Decoupled End-to-End Person Search [15.126269826140247]
  End-to-end person search aims to jointly detect and re-identify a target person in raw scene images with a unified model. The detection task unifies all persons while the re-id task discriminates different identities, resulting in conflict optimal objectives. Existing methods are still sub-optimal on one or two of the sub-tasks due to their partially decoupled models. A task-incremental person search network is proposed to incrementally construct an end-to-end model for the detection and re-id sub-task.
  arXiv  Detail & Related papers  (2023-09-10T09:00:28Z)
• LEAPS: End-to-End One-Step Person Search With Learnable Proposals [50.39493100627476]
  We propose an end-to-end one-step person search approach with learnable proposals, named LEAPS. Given a set of sparse and learnable proposals, LEAPS employs a dynamic person search head to directly perform person detection and corresponding re-id feature generation without non-maximum suppression post-processing.
  arXiv  Detail & Related papers  (2023-03-21T13:59:32Z)
• Sequential Transformer for End-to-End Person Search [4.920657401819193]
  Person search aims to simultaneously localize and recognize a target person from realistic and uncropped gallery images. In this paper, we propose a novel Sequential Transformer (SeqTR) for end-to-end person search to deal with this challenge. Our SeqTR contains a detection transformer and a novel re-ID transformer that sequentially addresses detection and re-ID tasks.
  arXiv  Detail & Related papers  (2022-11-06T09:32:30Z)
• Subtask-dominated Transfer Learning for Long-tail Person Search [12.311100923753449]
  Person search unifies person detection and person re-identification (Re-ID) to locate query persons from panoramic gallery images. One major challenge comes from the imbalanced long-tail person identity distributions. We propose a Subtask-dominated Transfer Learning (STL) method to solve this problem.
  arXiv  Detail & Related papers  (2021-12-01T14:34:48Z)
• Diverse Knowledge Distillation for End-to-End Person Search [81.4926655119318]
  Person search aims to localize and identify a specific person from a gallery of images. Recent methods can be categorized into two groups, i.e., two-step and end-to-end approaches. We propose a simple yet strong end-to-end network with diverse knowledge distillation to break the bottleneck.
  arXiv  Detail & Related papers  (2020-12-21T09:04:27Z)
• Deep Learning for Person Re-identification: A Survey and Outlook [233.36948173686602]
  Person re-identification (Re-ID) aims at retrieving a person of interest across multiple non-overlapping cameras. By dissecting the involved components in developing a person Re-ID system, we categorize it into the closed-world and open-world settings.
  arXiv  Detail & Related papers  (2020-01-13T12:49:22Z)

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.