Papers › BLT: Balancing Long-Tailed Datasets with Adversarially-Perturbed Images
BLT: Balancing Long-Tailed Datasets with Adversarially-Perturbed Images
Jedrzej Kozerawski, Victor Fragoso, Nikolaos Karianakis, Gaurav Mittal, Matthew Turk, Mei Chen
Real visual-world datasets tend to have few classes with large numbers of samples (i.e., head classes) and many others with smaller numbers of samples (i.e., tail classes). Unfortunately, this imbalance enables a visual recognition system to perform well on head classes but poorly on tail classes. To alleviate this imbalance, we present BLT, a novel data augmentation technique that generates extra training samples for tail classes to improve the generalization performance of a classifier. Unlike prior long-tail approaches that rely on generative models (e.g., GANs or VQ-VAEs) to augment a dataset, BLT uses a gradient-ascent based image generation algorithm that requires significantly less training time and computational resources. BLT avoids the use of dedicated generative networks, which adds significant computational overhead and require elaborate training procedures. Our experiments on natural and synthetic long-tailed datasets and across different network architectures demonstrate that BLT consistently improves the average classification performance of tail classes by 11% w.r.t. the common approach that balances the dataset by oversampling tail-class images. BLT maintains the accuracy on head classes while improving the performance on tail classes.
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 |
|---|---|---|---|---|---|---|---|
| Long-tail Learning | ImageNet-LT | BLT (DenseNet-121) | Top-1 Accuracy | 44.7 | #57 of 69 | Archive leaderboard | report |
| Long-tail Learning | ImageNet-LT | BLT (ResNet-10) | Top-1 Accuracy | 38.0 | #66 of 69 | 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