4 papers
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…
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…
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…
Masking Strategies for Background Bias Removal in Computer Vision Models
Ananthu Aniraj, Cassio F. Dantas, Dino Ienco +1
Models for fine-grained image classification tasks, where the difference between some classes can be extremely subtle and the number of samples per class tends to be low, are parti…