Transfer Learning with Dynamic Adversarial Adaptation Network

By Chaohui Yu, Jindong Wang, Yiqiang Chen, Meiyu Huang. Industrial Conference on Data Mining, 2019

388 citations recorded by the source corpus.

The recent advances in deep transfer learning reveal that adversarial learning can be embedded into deep networks to learn more transferable features to reduce the distribution discrepancy between two domains. Existing adversarial domain adaptation methods either learn a single domain discriminator to align the global source and target distributions, or pay attention to align subdomains based on multiple discriminators. However, in real applications, the marginal (global) and conditional (local) distributions between domains are often contributing differently to the adaptation. There is currently no method to dynamically and quantitatively evaluate the relative importance of these two distributions for adversarial learning. In this paper, we propose a novel Dynamic Adversarial Adaptation Network (DAAN) to dynamically learn domain-invariant representations while quantitatively evaluate the relative importance of global and local domain distributions. To the best of our knowledge, DAAN is the first attempt to perform dynamic adversarial distribution adaptation for deep adversarial learning. DAAN is extremely easy to implement and train in real applications. We theoretically analyze the effectiveness of DAAN, and it can also be explained in an attention strategy. Extensive experiments demonstrate that DAAN achieves better classification accuracy compared to state-of-the-art deep and adversarial methods. Results also imply the necessity and effectiveness of the dynamic distribution adaptation in adversarial transfer learning.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/c83ceff089e5c4493c79bb12b5f162478d526449

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. Mingsheng Long
2. Jianmin Wang
3. Zhangjie Cao
4. Jiashi Feng
5. Kate Saenko
6. Dacheng Tao
7. Tao Qin
8. Yi Yang

Citations in the corpus

• AdaRNN: Adaptive Learning and Forecasting of Time Series (2021, methodology): “We use “DANN-RNN” to denote popular domainadversarial training methods such as RevGrad [12] and DAAN [52].”
• Graph Information Aggregation Cross-Domain Few-Shot Learning for Hyperspectral Image Classification (2022, methodology): “…algorithms, including SVM, with the radial basis function (RBF) kernel, 3-dimensional CNN (3DCNN) [41], patch-to-patch CNN (PToP CNN) [11], DSAN [18], dynamic adversarial adaptation network (DAAN) [42], distribution propagation graph network (DPGN) [43], DFSL [33], RN-FSC [34], and DCFSL [40].”
• Reliable Weighted Optimal Transport for Unsupervised Domain Adaptation (2020, positive): “DANN [48] dynamically aligns the adversarial representations.”
• A Survey of Unsupervised Deep Domain Adaptation (2018, background): “While domain adaptation methods commonly align feature distributions, a different line of research aligns the joint or conditional distribution of the feature and label spaces instead [44, 47, 50, 148, 151, 154, 233, 267].”
• A Comprehensive Survey on Transfer Learning (2019, neutral): “[161] proposed a dynamic adversarial adaptation network.”
• Single-Source Domain Expansion Network for Cross-Scene Hyperspectral Image Classification (2022, methodology): “To evaluate the performance of SDEnet with only SD used for training, relevant algorithms including DAAN, MRAN, DSAN, HTCNN, PDEN, LDSDG and SagNet are used for comparison.”