Papers › Better Generalized Few-Shot Learning Even Without Base Data
Better Generalized Few-Shot Learning Even Without Base Data
Seong-Woong Kim, Dong-Wan Choi
This paper introduces and studies zero-base generalized few-shot learning (zero-base GFSL), which is an extreme yet practical version of few-shot learning problem. Motivated by the cases where base data is not available due to privacy or ethical issues, the goal of zero-base GFSL is to newly incorporate the knowledge of few samples of novel classes into a pretrained model without any samples of base classes. According to our analysis, we discover the fact that both mean and variance of the weight distribution of novel classes are not properly established, compared to those of base classes. The existing GFSL methods attempt to make the weight norms balanced, which we find helps only the variance part, but discard the importance of mean of weights particularly for novel classes, leading to the limited performance in the GFSL problem even with base data. In this paper, we overcome this limitation by proposing a simple yet effective normalization method that can effectively control both mean and variance of the weight distribution of novel classes without using any base samples and thereby achieve a satisfactory performance on both novel and base classes. Our experimental results somewhat surprisingly show that the proposed zero-base GFSL method that does not utilize any base samples even outperforms the existing GFSL methods that make the best use of base data. Our implementation is available at: https://github.com/bigdata-inha/Zero-Base-GFSL.
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 |
|---|---|---|---|---|---|---|---|
| Generalized Few-Shot Learning | AwA2 | MVCN | Per-Class Accuracy (1-shot) | 69.9 | #1 of 6 | Archive leaderboard | report |
| Generalized Few-Shot Learning | AwA2 | MVCN | Per-Class Accuracy (10-shots) | 82.2 | #1 of 6 | Archive leaderboard | report |
| Generalized Few-Shot Learning | AwA2 | MVCN | Per-Class Accuracy (2-shots) | 76.4 | #1 of 6 | Archive leaderboard | report |
| Generalized Few-Shot Learning | AwA2 | MVCN | Per-Class Accuracy (5-shots) | 81.2 | #1 of 6 | Archive leaderboard | report |
| Generalized Few-Shot Learning | CUB | MVCN | Per-Class Accuracy (2-shots) | 61.6 | #1 of 5 | Archive leaderboard | report |
| Generalized Few-Shot Learning | CUB | MVCN | Per-Class Accuracy (1-shot) | 57.3 | #1 of 5 | Archive leaderboard | report |
| Generalized Few-Shot Learning | CUB | MVCN | Per-Class Accuracy (10-shots) | 67.8 | #1 of 5 | Archive leaderboard | report |
| Generalized Few-Shot Learning | CUB | MVCN | Per-Class Accuracy (20-shots) | - | #1 of 5 | Archive leaderboard | report |
| Generalized Few-Shot Learning | CUB | MVCN | Per-Class Accuracy (5-shots) | 65.4 | #1 of 5 | 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