Papers › Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by...
Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images
Shiran Zada, Itay Benou, Michal Irani
Despite remarkable progress on visual recognition tasks, deep neural-nets still struggle to generalize well when training data is scarce or highly imbalanced, rendering them extremely vulnerable to real-world examples. In this paper, we present a surprisingly simple yet highly effective method to mitigate this limitation: using pure noise images as additional training data. Unlike the common use of additive noise or adversarial noise for data augmentation, we propose an entirely different perspective by directly training on pure random noise images. We present a new Distribution-Aware Routing Batch Normalization layer (DAR-BN), which enables training on pure noise images in addition to natural images within the same network. This encourages generalization and suppresses overfitting. Our proposed method significantly improves imbalanced classification performance, obtaining state-of-the-art results on a large variety of long-tailed image classification datasets (CIFAR-10-LT, CIFAR-100-LT, ImageNet-LT, Places-LT, and CelebA-5). Furthermore, our method is extremely simple and easy to use as a general new augmentation tool (on top of existing augmentations), and can be incorporated in any training scheme. It does not require any specialized data generation or training procedures, thus keeping training fast and efficient.
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 | CIFAR-10-LT (ρ=100) | OPeN (WideResNet-28-10) | Error Rate | 13.9 | #8 of 28 | Archive leaderboard | report |
| Long-tail Learning | CIFAR-10-LT (ρ=50) | OPeN (WideResNet-28-10) | Error Rate | 10.8 | #4 of 8 | Archive leaderboard | report |
| Long-tail Learning | CIFAR-100-LT (ρ=100) | OPeN (WideResNet-28-10) | Error Rate | 45.8 | #13 of 66 | Archive leaderboard | report |
| Long-tail Learning | CIFAR-100-LT (ρ=50) | OPeN (WideResNet-28-10) | Error Rate | 40.2 | #10 of 25 | Archive leaderboard | report |
| Long-tail Learning | CelebA-5 | OPeN (WideResNet-28-10) | Error Rate | 19.1 | #1 of 1 | Archive leaderboard | report |
| Long-tail Learning | ImageNet-LT | OPeN (ResNeXt-50) | Top-1 Accuracy | 55.1 | #38 of 69 | Archive leaderboard | report |
| Long-tail Learning | Places-LT | OPeN (ResNet-152) | Top-1 Accuracy | 40.5 | #17 of 29 | 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