Distant Supervised Centroid Shift: A Simple and Efficient Approach to Visual Domain Adaptation

By Jian Liang, Ran He, Zhenan Sun, Tien-Ping Tan. 2019

92 citations recorded by the source corpus.

Conventional domain adaptation methods usually resort to deep neural networks or subspace learning to find invariant representations across domains. However, most deep learning methods highly rely on large-size source domains and are computationally expensive to train, while subspace learning methods always have a quadratic time complexity that suffers from the large domain size. This paper provides a simple and efficient solution, which could be regarded as a well-performing baseline for domain adaptation tasks. Our method is built upon the nearest centroid classifier, seeking a subspace where the centroids in the target domain are moderately shifted from those in the source domain. Specifically, we design a unified objective without accessing the source domain data and adopt an alternating minimization scheme to iteratively discover the pseudo target labels, invariant subspace, and target centroids. Besides its privacy-preserving property (distant supervision), the algorithm is provably convergent and has a promising linear time complexity. In addition, the proposed method can be readily extended to multi-source setting and domain generalization, and it remarkably enhances popular deep adaptation methods by borrowing the learned transferable features. Extensive experiments on several benchmarks including object, digit, and face recognition datasets validate that our methods yield state-of-the-art results in various domain adaptation tasks.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

1. Pietro Zanuttigh
2. Umberto Michieli
3. Jian Liang
4. Dapeng Hu
5. Ran He
6. Jiashi Feng
7. Zhaoxiang Zhang
8. Yuxi Wang

In Computer Vision and Pattern Recognition

1. Pietro Zanuttigh
2. Umberto Michieli
3. Jian Liang
4. Ran He
5. Dapeng Hu
6. Zhaoxiang Zhang
7. Jiashi Feng
8. Yuxi Wang

Citations in the corpus

• Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations (2021, methodology): “also recalls features clustering (if features belong to the same class) and separation (if features belong to different classes), which has been recently applied to adapt semantic segmentation models across domains [29, 37, 61].”
• Give Me Your Trained Model: Domain Adaptive Semantic Segmentation without Source Data (2021, methodology): “To remedy this issue, various domain alignment strategies are proposed in [8, 2, 9–11].”
• Source Data-Absent Unsupervised Domain Adaptation Through Hypothesis Transfer and Labeling Transfer (2020, methodology): “like that in Minimum Centroid Shift (MCS) [63] where target-specific centroids and pseudo labels are alternately updated via optimizing the intra-class divergence minimization loss.”
• A Comprehensive Survey on Test-Time Adaptation Under Distribution Shifts (2023, unknown): “Several methods [119], [120], [121] follow this learning mechanism and adapt the source”
• A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation (2020, unknown): “8 MCS [23] 55.”
• Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation (2020, methodology): “To our best knowledge, (Chidlovskii et al., 2016; Liang et al., 2019) introduce similar settings as ours to the unsupervised DA problem, but they may not work well enough since they do not incorporate the end-to-end feature learning module inside.”