← Search

Cassio F. Dantas

2 accepted papers

2024

PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers

ECCV 2024oral

"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 driven by a fine-grained classification task make very restrictive assumptions on the geometric properties of the discov…

2023

PDiscoNet: Semantically consistent part discovery for fine-grained recognition

ICCV 2023poster

Fine-grained classification often requires recognizing specific object parts, such as beak shape and wing patterns for birds. Encouraging a fine-grained classification model to first detect such parts and then using them to infer the class could help us gauge whether the model is indeed looking at t…

Cited by 16PDFcodeScholar