Papers › Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learning
Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learning
Yuqian Fu, Yu Xie, Yanwei Fu, Jingjing Chen, Yu-Gang Jiang
Previous few-shot learning (FSL) works mostly are limited to natural images of general concepts and categories. These works assume very high visual similarity between the source and target classes. In contrast, the recently proposed cross-domain few-shot learning (CD-FSL) aims at transferring knowledge from general nature images of many labeled examples to novel domain-specific target categories of only a few labeled examples. The key challenge of CD-FSL lies in the huge data shift between source and target domains, which is typically in the form of totally different visual styles. This makes it very nontrivial to directly extend the classical FSL methods to address the CD-FSL task. To this end, this paper studies the problem of CD-FSL by spanning the style distributions of the source dataset. Particularly, wavelet transform is introduced to enable the decomposition of visual representations into low-frequency components such as shape and style and high-frequency components e.g., texture. To make our model robust to visual styles, the source images are augmented by swapping the styles of their low-frequency components with each other. We propose a novel Style Augmentation (StyleAug) module to implement this idea. Furthermore, we present a Self-Supervised Learning (SSL) module to ensure the predictions of style-augmented images are semantically similar to the unchanged ones. This avoids the potential semantic drift problem in exchanging the styles. Extensive experiments on two CD-FSL benchmarks show the effectiveness of our method. Our codes and models will be released.
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 | wave-SAN | 5 shot | 70.31 | #3 of 9 | Archive leaderboard | report |
| Cross-Domain Few-Shot | ChestX | wave-SAN | 5 shot | 25.63 | #5 of 11 | Archive leaderboard | report |
| Cross-Domain Few-Shot | CropDisease | wave-SAN | 5 shot | 89.70 | #5 of 9 | Archive leaderboard | report |
| Cross-Domain Few-Shot | EuroSAT | wave-SAN | 5 shot | 85.22 | #5 of 11 | Archive leaderboard | report |
| Cross-Domain Few-Shot | ISIC2018 | wave-SAN | 5 shot | 44.93 | #7 of 11 | Archive leaderboard | report |
| Cross-Domain Few-Shot | Places | wave-SAN | 5 shot | 76.88 | #3 of 8 | Archive leaderboard | report |
| Cross-Domain Few-Shot | Plantae | wave-SAN | 5 shot | 57.72 | #5 of 8 | Archive leaderboard | report |
| Cross-Domain Few-Shot | cars | wave-SAN | 5 shot | 46.11 | #7 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.
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