Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization

By Shujun Wang, Lequan Yu, Caizi Li, Chi-Wing Fu, P. Heng. 2020

231 citations recorded by the source corpus.

The generalization capability of neural networks across domains is crucial for real-world applications. We argue that a generalized object recognition system should well understand the relationships among different images and also the images themselves at the same time. To this end, we present a new domain generalization framework that learns how to generalize across domains simultaneously from extrinsic relationship supervision and intrinsic self-supervision for images from multi-source domains. To be specific, we formulate our framework with feature embedding using a multi-task learning paradigm. Besides conducting the common supervised recognition task, we seamlessly integrate a momentum metric learning task and a self-supervised auxiliary task to collectively utilize the extrinsic supervision and intrinsic supervision. Also, we develop an effective momentum metric learning scheme with K-hard negative mining to boost the network to capture image relationship for domain generalization. We demonstrate the effectiveness of our approach on two standard object recognition benchmarks VLCS and PACS, and show that our methods achieve state-of-the-art performance.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

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. Yu Qiao
2. Ziwei Liu
3. Chen Change Loy
4. Kaiyang Zhou
5. Tao A. Xiang
6. P. Heng
7. Qi-Yan Dou
8. Jing Qin

In Computer Vision and Pattern Recognition

1. Yu Qiao
2. Luc Van Gool
3. Chen Change Loy
4. Tao A. Xiang
5. Xiaogang Wang
6. Qi Tian
7. Dacheng Tao
8. Yi Yang

In Radiology, Nuclear Medicine and Imaging

1. P. Heng
2. Jing Qin
3. Qi-Yan Dou
4. Cheng Chen
5. Quande Liu
6. Ziwei Liu
7. Peng Cui
8. Yu Qiao

Citations in the corpus

• SWAD: Domain Generalization by Seeking Flat Minima (2021, neutral): “MASF [14] 82.7 - - - - - DMG [33] 83.4 - - - 43.6 - MetaReg [15] 83.6 - - - 43.6 - ER [12] 85.3 - - - - - pAdaIN [47] 85.4 - - - - - EISNet [48] 85.8 - - - - - DSON [30] 86.”
• Deep Stable Learning for Out-Of-Distribution Generalization (2021, background): “Recently, such distribution (domain) shift problems have been intensively studied in the domain generalization (DG) literature [41, 17, 25, 62, 31, 33].”
• A Fourier-based Framework for Domain Generalization (2021, background): “[45] further extend this work by incorporating a momentum metric learning scheme.”
• Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection (2022, methodology): “Self-supervised tasks have been shown effective for improving generalization in previous works [7, 50].”
• FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space (2021, methodology): “There are other methods tackling DG by manipulating deep neural network architectures [19, 23, 35], leveraging self-supervision signals [3, 54], designing training heuristics [17, 25], or conducting data augmentations [48, 53, 60, 61], which are free from requirement of data centralization.”
• Domain Generalization: A Survey (2021, methodology): “Though being different in terms of the problem setup, the MTL paradigm has been exploited in some DG methods, notably for those based on self-supervised learning [49], [134], [135].”