works on
diffusion models 1feature discrepancy 1logit discrepancy 1out-of-distribution detection 1representation learning 1subspace refinement 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.CV2026

Beyond Perceptual Distance: Discrepancy Assessment on Deep Representation for Out-of-Distribution Detection with Diffusion Model

Kun Fang, Zuopeng Yang, Haibo Hu +3

The paper introduces DDR, a method that evaluates the difference between an input image and its diffusion‑model reconstruction using the classifier’s deep feature and logit represe…