Gradually Vanishing Bridge for Adversarial Domain Adaptation

By Shuhao Cui, Shuhui Wang, Junbao Zhuo, Chi Su, Qingming Huang, Qi Tian. 2020

288 citations recorded by the source corpus.

In unsupervised domain adaptation, rich domain-specific characteristics bring great challenge to learn domain-invariant representations. However, domain discrepancy is considered to be directly minimized in existing solutions, which is difficult to achieve in practice. Some methods alleviate the difficulty by explicitly modeling domain-invariant and domain-specific parts in the representations, but the adverse influence of the explicit construction lies in the residual domain-specific characteristics in the constructed domain-invariant representations. In this paper, we equip adversarial domain adaptation with Gradually Vanishing Bridge (GVB) mechanism on both generator and discriminator. On the generator, GVB could not only reduce the overall transfer difficulty, but also reduce the influence of the residual domain-specific characteristics in domain-invariant representations. On the discriminator, GVB contributes to enhance the discriminating ability, and balance the adversarial training process. Experiments on three challenging datasets show that our GVB methods outperform strong competitors, and cooperate well with other adversarial methods. The code is available at https://github.com/cuishuhao/GVB.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Infectious Diseases, Representation & Self-Supervised Learning, Safety, Robustness & Interpretability

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. Yunchao Wei
2. Jiashi Feng
3. Yi Yang
4. Jian Liang
5. Guoliang Kang
6. Dapeng Hu
7. Ran He
8. Yunbo Wang

In Computer Vision and Pattern Recognition

1. Jiashi Feng
2. Yunchao Wei
3. Yi Yang
4. Luc Van Gool
5. Trevor Darrell
6. Jian Liang
7. Dacheng Tao
8. Ran He

In Infectious Diseases

1. Jiashi Feng

In Representation & Self-Supervised Learning

1. Jian Liang
2. Ran He
3. Yi Zhu
4. Yunbo Wang
5. Guangrui Li
6. Jiashi Feng
7. Guoliang Kang
8. Yunchao Wei

In Safety, Robustness & Interpretability

1. Jian Liang
2. Jiashi Feng
3. Yunchao Wei
4. Yi Yang
5. Kate Saenko

Citations in the corpus

• Domain Consensus Clustering for Universal Domain Adaptation (2021, background): “Some recent works take advantage of adversarial training to promote the alignment in the input space [11, 23, 25, 20, 10] or feature space [58, 44, 6, 18, 38, 64, 43].”
• Source Data-Absent Unsupervised Domain Adaptation Through Hypothesis Transfer and Labeling Transfer (2020, methodology): “Following previous works [102], [104], we further adopt the ResNet-50 [118] backbone to validate the effectiveness of our methods.”