Subtask-dominated Transfer Learning for Long-tail Person Search
- URL: http://arxiv.org/abs/2112.00527v1
- Date: Wed, 1 Dec 2021 14:34:48 GMT
- Title: Subtask-dominated Transfer Learning for Long-tail Person Search
- Authors: Chuang Liu, Hua Yang, Qin Zhou, Shibao Zheng
- Abstract summary: 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.
- Score: 12.311100923753449
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Person search unifies person detection and person re-identification (Re-ID)
to locate query persons from the panoramic gallery images. One major challenge
comes from the imbalanced long-tail person identity distributions, which
prevents the one-step person search model from learning discriminative person
features for the final re-identification. However, it is under-explored how to
solve the heavy imbalanced identity distributions for the one-step person
search. Techniques designed for the long-tail classification task, for example,
image-level re-sampling strategies, are hard to be effectively applied to the
one-step person search which jointly solves person detection and Re-ID subtasks
with a detection-based multi-task framework. To tackle this problem, we propose
a Subtask-dominated Transfer Learning (STL) method. The STL method solves the
long-tail problem in the pretraining stage of the dominated Re-ID subtask and
improves the one-step person search by transfer learning of the pretrained
model. We further design a Multi-level RoI Fusion Pooling layer to enhance the
discrimination ability of person features for the one-step person search.
Extensive experiments on CUHK-SYSU and PRW datasets demonstrate the superiority
and effectiveness of the proposed method.
Related papers
- Divide and Conquer: Hybrid Pre-training for Person Search [40.13016375392472]
We propose a hybrid pre-training framework specifically designed for person search using sub-task data only.
Our model can achieve significant improvements across diverse protocols, such as person search method, fine-tuning data, pre-training data and model backbone.
Our code and pre-trained models are released for plug-and-play usage to the person search community.
arXiv Detail & Related papers (2023-12-13T08:33:50Z) - 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) - 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) - Unsupervised Person Re-Identification: A Systematic Survey of Challenges
and Solutions [64.68497473454816]
Unsupervised person Re-ID has drawn increasing attention for its potential to address the scalability issue in person Re-ID.
Unsupervised person Re-ID is challenging primarily due to lacking identity labels to supervise person feature learning.
This survey review recent works on unsupervised person Re-ID from the perspective of challenges and solutions.
arXiv Detail & Related papers (2021-09-01T00:01:35Z) - Making Person Search Enjoy the Merits of Person Re-identification [12.311100923753449]
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.
arXiv Detail & Related papers (2021-08-24T06:00:13Z) - Decoupled and Memory-Reinforced Networks: Towards Effective Feature
Learning for One-Step Person Search [65.51181219410763]
One-step methods have been developed to handle pedestrian detection and identification sub-tasks using a single network.
There are two major challenges in the current one-step approaches.
We propose a decoupled and memory-reinforced network (DMRNet) to overcome these problems.
arXiv Detail & Related papers (2021-02-22T06:19:45Z) - Unsupervised Noisy Tracklet Person Re-identification [100.85530419892333]
We present a novel selective tracklet learning (STL) approach that can train discriminative person re-id models from unlabelled tracklet data.
This avoids the tedious and costly process of exhaustively labelling person image/tracklet true matching pairs across camera views.
Our method is particularly more robust against arbitrary noisy data of raw tracklets therefore scalable to learning discriminative models from unconstrained tracking data.
arXiv Detail & Related papers (2021-01-16T07:31:00Z) - 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) - FMT:Fusing Multi-task Convolutional Neural Network for Person Search [33.91664470686695]
We propose a fusing multi-task convolutional neural network(FMT-CNN) to tackle the correlation and heterogeneity of detection and re-identification.
Experiment results on CUHK-SYSU Person Search dataset show that the performance of our proposed method is superior to state-of-the-art approaches.
arXiv Detail & Related papers (2020-03-01T05:20:47Z) - Intra-Camera Supervised Person Re-Identification [87.88852321309433]
We propose a novel person re-identification paradigm based on an idea of independent per-camera identity annotation.
This eliminates the most time-consuming and tedious inter-camera identity labelling process.
We formulate a Multi-tAsk mulTi-labEl (MATE) deep learning method for Intra-Camera Supervised (ICS) person re-id.
arXiv Detail & Related papers (2020-02-12T15:26:33Z)
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.