A naukri.com initiative
Arxiv
12h
50
Image Credit: Arxiv
Gradient Short-Circuit: Efficient Out-of-Distribution Detection via Feature Intervention
- Out-of-Distribution (OOD) detection is crucial for deploying deep models safely in open-world environments.
- A salient gradient phenomenon has been observed during inference on a model trained only with In-Distribution (ID) data.
- Based on this observation, a technique has been proposed to short-circuit feature coordinates exploited by spurious gradients in OOD samples while preserving ID classification.
- Experiments on OOD benchmarks demonstrate significant improvements with this approach, which is lightweight and integrates seamlessly into the standard inference pipeline.
Read Full Article
3 Likes
For uninterrupted reading, download the app