Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID

Abstract

Domain adaptive object re-ID aims to transfer the learned knowledge from the labeled source domain to the unlabeled target domain to tackle the open-class re-identification problems. Although state-of-the-art pseudo-label-based methods have achieved great success, they did not make full use of all valuable information because of the domain gap and unsatisfying clustering performance. To solve these problems, we propose a novel self-paced contrastive learning framework with hybrid memory. The hybrid memory dynamically generates source-domain class-level, target-domain cluster-level and un-clustered instance-level supervisory signals for learning feature representations. Different from the conventional contrastive learning strategy, the proposed framework jointly distinguishes source-domain classes, and target-domain clusters and un-clustered instances. Most importantly, the proposed self-paced method gradually creates more reliable clusters to refine the hybrid memory and learning targets, and is shown to be the key to our outstanding performance. Our method outperforms state-of-the-arts on multiple domain adaptation tasks of object re-ID and even boosts the performance on the source domain without any extra annotations. Our generalized version on unsupervised object re-ID surpasses state-of-the-art algorithms by considerable 16.7% and 7.9% on Market-1501 and MSMT17 benchmarks.

arXiv commentAccepted in NeurIPS 2020. Code available: https://github.com/yxgeee/SpCL

References in corpus (9)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Representation Learning with Contrastive Predictive Coding
• Learning deep representations by mutual information estimation and maximization
• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
• Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification
• FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification
• Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation
• Simulating Content Consistent Vehicle Datasets with Attribute Descent
• Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification

Cited by in corpus (20)

• Hybrid Dynamic Contrast and Probability Distillation for Unsupervised Person Re-Id
• Complementary Pseudo Labels For Unsupervised Domain Adaptation On Person Re-identification
• Unsupervised Person Re-identification with Stochastic Training Strategy
• DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations
• CA-Jaccard: Camera-aware Jaccard Distance for Person Re-identification
• Hierarchical Skeleton Meta-Prototype Contrastive Learning with Hard Skeleton Mining for Unsupervised Person Re-Identification
• Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship Attribution
• Cross-domain few-shot learning with unlabelled data
• ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection
• Re-identification = Retrieval + Verification: Back to Essence and Forward with a New Metric
• Camera-aware Style Separation and Contrastive Learning for Unsupervised Person Re-identification
• Improving Unsupervised Domain Adaptive Re-Identification via Source-Guided Selection of Pseudo-Labeling Hyperparameters
• Machine learning with limited data
• TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification
• Deep Contrastive Graph Representation via Adaptive Homotopy Learning
• Discriminability Distillation in Group Representation Learning
• CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble Fusion
• Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification
• Progressive Stage-wise Learning for Unsupervised Feature Representation Enhancement
• Test-time Similarity Modification for Person Re-identification toward Temporal Distribution Shift