Generalizable Re-Identification from Videos with Cycle Association
- URL: http://arxiv.org/abs/2211.03663v2
- Date: Tue, 8 Nov 2022 15:29:13 GMT
- Title: Generalizable Re-Identification from Videos with Cycle Association
- Authors: Zhongdao Wang, Zhaopeng Dou, Jingwei Zhang, Liang Zheng, Yifan Sun,
Yali Li, Shengjin Wang
- Abstract summary: We propose Cycle Association (CycAs) as a scalable self-supervised learning method for re-ID with low training complexity.
We construct a large-scale unlabeled re-ID dataset named LMP-video, tailored for the proposed method.
CycAs learns re-ID features by enforcing cycle consistency of instance association between temporally successive video frame pairs.
- Score: 60.920036335996414
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In this paper, we are interested in learning a generalizable person
re-identification (re-ID) representation from unlabeled videos. Compared with
1) the popular unsupervised re-ID setting where the training and test sets are
typically under the same domain, and 2) the popular domain generalization (DG)
re-ID setting where the training samples are labeled, our novel scenario
combines their key challenges: the training samples are unlabeled, and
collected form various domains which do no align with the test domain. In other
words, we aim to learn a representation in an unsupervised manner and directly
use the learned representation for re-ID in novel domains. To fulfill this
goal, we make two main contributions: First, we propose Cycle Association
(CycAs), a scalable self-supervised learning method for re-ID with low training
complexity; and second, we construct a large-scale unlabeled re-ID dataset
named LMP-video, tailored for the proposed method. Specifically, CycAs learns
re-ID features by enforcing cycle consistency of instance association between
temporally successive video frame pairs, and the training cost is merely linear
to the data size, making large-scale training possible. On the other hand, the
LMP-video dataset is extremely large, containing 50 million unlabeled person
images cropped from over 10K Youtube videos, therefore is sufficient to serve
as fertile soil for self-supervised learning. Trained on LMP-video, we show
that CycAs learns good generalization towards novel domains. The achieved
results sometimes even outperform supervised domain generalizable models.
Remarkably, CycAs achieves 82.2% Rank-1 on Market-1501 and 49.0% Rank-1 on
MSMT17 with zero human annotation, surpassing state-of-the-art supervised DG
re-ID methods. Moreover, we also demonstrate the superiority of CycAs under the
canonical unsupervised re-ID and the pretrain-and-finetune scenarios.
Related papers
- Unleashing the Potential of Unsupervised Pre-Training with
Intra-Identity Regularization for Person Re-Identification [10.045028405219641]
We design an Unsupervised Pre-training framework for ReID based on the contrastive learning (CL) pipeline, dubbed UP-ReID.
We introduce an intra-identity (I$2$-)regularization in the UP-ReID, which is instantiated as two constraints coming from global image aspect and local patch aspect.
Our UP-ReID pre-trained model can significantly benefit the downstream ReID fine-tuning and achieve state-of-the-art performance.
arXiv Detail & Related papers (2021-12-01T07:16:37Z) - Semi-Supervised Domain Generalizable Person Re-Identification [74.75528879336576]
Existing person re-identification (re-id) methods are stuck when deployed to a new unseen scenario.
Recent efforts have been devoted to domain adaptive person re-id where extensive unlabeled data in the new scenario are utilized in a transductive learning manner.
We aim to explore multiple labeled datasets to learn generalized domain-invariant representations for person re-id.
arXiv Detail & Related papers (2021-08-11T06:08:25Z) - Camera-aware Proxies for Unsupervised Person Re-Identification [60.26031011794513]
This paper tackles the purely unsupervised person re-identification (Re-ID) problem that requires no annotations.
We propose to split each single cluster into multiple proxies and each proxy represents the instances coming from the same camera.
Based on the camera-aware proxies, we design both intra- and inter-camera contrastive learning components for our Re-ID model.
arXiv Detail & Related papers (2020-12-19T12:37:04Z) - Multi-Domain Adversarial Feature Generalization for Person
Re-Identification [52.835955258959785]
We propose a multi-dataset feature generalization network (MMFA-AAE)
It is capable of learning a universal domain-invariant feature representation from multiple labeled datasets and generalizing it to unseen' camera systems.
It also surpasses many state-of-the-art supervised methods and unsupervised domain adaptation methods by a large margin.
arXiv Detail & Related papers (2020-11-25T08:03:15Z) - Semantics-Guided Clustering with Deep Progressive Learning for
Semi-Supervised Person Re-identification [58.01834972099855]
Person re-identification (re-ID) requires one to match images of the same person across camera views.
We propose a novel framework of Semantics-Guided Clustering with Deep Progressive Learning (SGC-DPL) to jointly exploit the above data.
Our approach is able to augment the labeled training data in the semi-supervised setting.
arXiv Detail & Related papers (2020-10-02T18:02:35Z) - CycAs: Self-supervised Cycle Association for Learning Re-identifiable
Descriptions [61.724894233252414]
This paper proposes a self-supervised learning method for the person re-identification (re-ID) problem.
Existing unsupervised methods usually rely on pseudo labels, such as those from video tracklets or clustering.
We introduce a different unsupervised method that allows us to learn pedestrian embeddings from raw videos, without resorting to pseudo labels.
arXiv Detail & Related papers (2020-07-15T09:52:35Z)
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.