Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-identification
This paper aims to learn a domain-generalizable (DG) person re-identification (ReID) representation from large-scale videos \textbf{without any annotation}. Prior DG ReID methods employ limited labeled data for training due to the high cost of annotation, which restricts further advances. To overcome the barriers of data and annotation, we propose to utilize large-scale unsupervised data for training. The key issue lies in how to mine identity information. To this end, we propose an Identity-seeking Self-supervised Representation learning (ISR) method. ISR constructs positive pairs from inter-frame images by modeling the instance association as a maximum-weight bipartite matching problem. A reliability-guided contrastive loss is further presented to suppress the adverse impact of noisy positive pairs, ensuring that reliable positive pairs dominate the learning process. The training cost of ISR scales approximately linearly with the data size, making it feasible to utilize large-scale data for training. The learned representation exhibits superior generalization ability. \textbf{Without human annotation and fine-tuning, ISR achieves 87.0\% Rank-1 on Market-1501 and 56.4\% Rank-1 on MSMT17}, outperforming the best supervised domain-generalizable method by 5.0\% and 19.5\%, respectively. In the pre-training$\rightarrow$fine-tuning scenario, ISR achieves state-of-the-art performance, with 88.4\% Rank-1 on MSMT17. The code is at \url{https://github.com/dcp15/ISR_ICCV2023_Oral}.
Code (2)
Tasks
Generalizable Person Re-identificationPerson Re-IdentificationRepresentation LearningSimilar Papers 제목 키워드 기반
A Study of the Generalizability of Self-Supervised Representations
Recent advancements in self-supervised learning (SSL) made it possible to learn generalizable visual representations from unlabeled data. The performance of Deep Learning models fine-tuned on pretrained SSL representatio…
Self-Supervised LearningTransfer LearningMonoSelfRecon: Purely Self-Supervised Explicit Generalizable 3D Reconstruction of Indoor Scenes from Monocular RGB Views
Current monocular 3D scene reconstruction (3DR) works are either fully-supervised, or not generalizable, or implicit in 3D representation. We propose a novel framework - MonoSelfRecon that for the first time achieves exp…
3D Reconstruction3D Scene ReconstructionDepth EstimationNeRFSELFI: Selective Fusion of Identity for Generalizable Deepfake Detection
Face identity provides a powerful signal for deepfake detection. Prior studies show that even when not explicitly modeled, classifiers often learn identity features implicitly. This has led to conflicting views: some sup…
DeepFake DetectionFace RecognitionFace SwappingStyle Normalization and Restitution for Generalizable Person Re-identification
Existing fully-supervised person re-identification (ReID) methods usually suffer from poor generalization capability caused by domain gaps. The key to solving this problem lies in filtering out identity-irrelevant interf…
DisentanglementDomain AdaptationDomain GeneralizationGeneralizable Person Re-identification+2Towards Unsupervised Domain Generalization for Face Anti-Spoofing
Generalizable face anti-spoofing (FAS) based on domain generalization (DG) has gained growing attention due to its robustness in real-world applications. However, these DG methods rely heavily on labeled source data,…
Domain GeneralizationFace Anti-Spoofing