3 papers
cs.CV2026
Metonymy in vision models undermines attention-based interpretability
Ananthu Aniraj, Cassio F. Dantas, Dino Ienco +2
Part-based reasoning is a classical strategy to make a computer vision model directly focus on the object parts that are relevant to the downstream task. In the context of deep lea…
cs.CV2025
Two-stage Vision Transformers and Hard Masking offer Robust Object Representations
Ananthu Aniraj, Cassio F. Dantas, Dino Ienco +1
Context can strongly affect object representations, sometimes leading to undesired biases, particularly when objects appear in out-of-distribution backgrounds at inference. At the…
cs.CV2024
PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers
Ananthu Aniraj, Cassio F. Dantas, Dino Ienco +1
Computer vision methods that explicitly detect object parts and reason on them are a step towards inherently interpretable models. Existing approaches that perform part discovery d…