DRAGS: Teaching Vision AI to Ignore the Noise

By Nuruzzaman Faruqui

·

Image-recognition AI can ace clean test images yet stumble on blurry or noisy ones. DRAGS is a simple training trick that tells the model to stop learning from the parts of an image that look like noise.

+1.39points of clean accuracy on CIFAR-10
3random seeds tested
ResNet-18backbone model

The problem

Deep vision models often break down when inputs are corrupted by noise, blur or occlusion. Common regularisers act uniformly across the whole image, rather than focusing on the problem areas.

What the research did

We introduced Dynamic Region-Aware Gradient Suppression (DRAGS). During training, it scores each location in a feature map, keeps only the most informative fraction, and stops learning signals from the rest, which are likely noisy or misleading.

What we found

On CIFAR-10 with a ResNet-18 model, DRAGS improved clean accuracy by 1.39 points over a strong baseline (64.15% ± 2.30 versus 62.76% ± 1.05 across three seeds) while maintaining robustness under common corruptions, with slight gains on Gaussian noise.

Who benefits

  • Engineers deploying vision AI in messy real-world conditions
  • Researchers in robust and trustworthy AI
  • Applications such as medical imaging and autonomous systems

Limits and what comes next

Gains are modest and tested on one dataset and model; the variance across seeds means larger studies are needed. This connects to my PhD focus on trustworthy AI.

The team

This research was led by Md Muntaqim Meherab with me and colleagues from Daffodil International University, South Dakota School of Mines and Technology, Islamic University of Technology and BUET.

Frequently asked questions

What does DRAGS do?

It stops a vision model learning from image regions that look noisy or misleading during training.

How much does it help?

About 1.39 points of clean accuracy on CIFAR-10 in the study.

Why does robustness matter?

Real-world images are often blurry or noisy, and AI must still work reliably.

About the author

Nuruzzaman Faruqui is an award-winning AI educator and researcher who has taught artificial intelligence and machine learning at university level since 2018. A two-time winner of the Excellence in Teaching Award (2023, 2024) and winner of the Best Researcher Award (2024) at Daffodil International University, he is now a doctoral researcher in AI at Monash University, Australia. He has published 53 papers and six books, and writes these articles to make AI research easy for everyone to understand. His teaching · About Zaman · Get in touch

Keep reading