Domain Generalization with Small Data

• Published in: International journal of computer vision Vol. 132; no. 8; pp. 3172 - 3190
• Main Authors: Chen, Kecheng, Gal, Elena, Yan, Hong, Li, Haoliang
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.08.2024
• Subjects: Artificial Intelligence; Computer Imaging; Computer Science; Image Processing and Computer Vision; Pattern Recognition; Pattern Recognition and Graphics; Vision; Small data; Healthcare; Medical imaging; Domain generalization
• ISSN: 0920-5691; 1573-1405
• DOI: 10.1007/s11263-024-02028-4

In this work, we propose to tackle the problem of domain generalization in the context of insufficient samples . Instead of extracting latent feature embeddings based on deterministic models, we propose to learn a domain-invariant representation based on the probabilistic framework by mapping each data point into probabilistic embeddings. Specifically, we first extend empirical maximum mean discrepancy (MMD) to a novel probabilistic MMD that can measure the discrepancy between mixture distributions (i.e., source domains) consisting of a series of latent distributions rather than latent points. Moreover, instead of imposing the contrastive semantic alignment (CSA) loss based on pairs of latent points, a novel probabilistic CSA loss encourages positive probabilistic embedding pairs to be closer while pulling other negative ones apart. Benefiting from the learned representation captured by probabilistic models, our proposed method can marriage the measurement on the distribution over distributions (i.e., the global perspective alignment) and the distribution-based contrastive semantic alignment (i.e., the local perspective alignment). Extensive experimental results on three challenging medical datasets show the effectiveness of our proposed method in the context of insufficient data compared with state-of-the-art methods.