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

By Yixiao Ge, Dapeng Chen, Feng Zhu, Rui Zhao, Hongsheng Li. 2020

670 citations recorded by the source corpus.

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 person re-ID surpasses state-of-the-art algorithms by considerable 16.2% and 14.6% on Market-1501 and DukeMTMC-reID benchmarks. Code is available at this https URL.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Layerwise Optimization by Gradient Decomposition for Continual Learning (2021, positive): “Layerwise gradient update strategy is also applied in meta-learning for rapid loss convergence on transfer learning [13, 14, 48] and few-shot learning [49, 28].”
ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection (2021, result): “In contrast to the intensive studies on UDA of the 2D image setting [10, 26, 17, 7, 32, 11, 12], few efforts [41] have been made to explore UDA for 3D detection.”
Discriminability Distillation in Group Representation Learning (2020, background): “It is also beneficial to perform person re-identification [61,39,18,16,17,33,15] from videos.”
Dual Contrastive Loss and Attention for GANs (2021, background): “Contrastive learning is shown to be an effective tool for unsupervised learning [61, 27, 87], conditional image synthesis [63, 40, 106], and domain adaptation [23].”
Boundary-aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval (2023, background): “Researchers pay more attention to the improvement of retrieval performance [3, 13, 25, 27, 28] and there exist several comprehensive benchmarks [12, 22].”
Cluster Contrast for Unsupervised Person Re-Identification (2021, methodology): “4, the clustering centroids of SPCL after each iteration can be obtained by ck ← 1 |Hk| ∑ ui∈Hk ui∈Q [mui + (1−m)q] + ∑ ui∈Hk ui /∈Q ui (8) whereQ denotes the query instance features set, which contains all the feature vectors of query images for one iteration.”
Complementary Relation Contrastive Distillation (2021, background): “Contrastive Learning serves as the core idea of several recent works on self-supervised representation learning [8, 16, 30, 20, 15, 44, 42, 13].”
Gradient Regularized Contrastive Learning for Continual Domain Adaptation (2020, background): “2017) and contrastive learning based approaches (Ge et al. 2020; Park et al. 2020; Kim et al. 2020).”