Papers › Adversarial Feature Augmentation for Cross-domain Few-shot Classification
Adversarial Feature Augmentation for Cross-domain Few-shot Classification
Yanxu Hu, Andy J. Ma
Existing methods based on meta-learning predict novel-class labels for (target domain) testing tasks via meta knowledge learned from (source domain) training tasks of base classes. However, most existing works may fail to generalize to novel classes due to the probably large domain discrepancy across domains. To address this issue, we propose a novel adversarial feature augmentation (AFA) method to bridge the domain gap in few-shot learning. The feature augmentation is designed to simulate distribution variations by maximizing the domain discrepancy. During adversarial training, the domain discriminator is learned by distinguishing the augmented features (unseen domain) from the original ones (seen domain), while the domain discrepancy is minimized to obtain the optimal feature encoder. The proposed method is a plug-and-play module that can be easily integrated into existing few-shot learning methods based on meta-learning. Extensive experiments on nine datasets demonstrate the superiority of our method for cross-domain few-shot classification compared with the state of the art. Code is available at https://github.com/youthhoo/AFA_For_Few_shot_learning
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Cross-Domain Few-Shot | CUB | AFA | 5 shot | 68.25 | #6 of 9 | Archive leaderboard | report |
| Cross-Domain Few-Shot | ChestX | AFA | 5 shot | 25.02 | #9 of 11 | Archive leaderboard | report |
| Cross-Domain Few-Shot | CropDisease | AFA | 5 shot | 88.06 | #8 of 9 | Archive leaderboard | report |
| Cross-Domain Few-Shot | EuroSAT | AFA | 5 shot | 85.58 | #4 of 11 | Archive leaderboard | report |
| Cross-Domain Few-Shot | ISIC2018 | AFA | 5 shot | 46.01 | #5 of 11 | Archive leaderboard | report |
| Cross-Domain Few-Shot | Places | AFA | 5 shot | 76.21 | #5 of 8 | Archive leaderboard | report |
| Cross-Domain Few-Shot | Plantae | AFA | 5 shot | 54.26 | #6 of 8 | Archive leaderboard | report |
| Cross-Domain Few-Shot | cars | AFA | 5 shot | 49.28 | #5 of 8 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections