PDiscoNet: Semantically consistent part discovery for fine-grained recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

PDiscoNet: Semantically consistent part discovery for fine-grained recognition


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 the right details better than with interpretability methods that provide a single attribution map. We propose PDiscoNet to discover object parts by using only image-level class labels along with priors encouraging the parts to be: discriminative, compact, distinct from each other, equivariant to rigid transforms, and active in at least some of the images. In addition to using the appropriate losses to encode these priors, we propose to use part-dropout, where full part feature vectors are dropped at once to prevent a single part from dominating in the classification, and part feature vector modulation, which makes the information coming from each part distinct from the perspective of the classifier. Our results on CUB, CelebA, and PartImageNet show that the proposed method provides substantially better part discovery performance than previous methods while not requiring any additional hyper-parameter tuning and without penalizing the classification performance. The code is available at https://github.com/robertdvdk/part_detection
Fichier principal
Vignette du fichier
ICCV_Camera_ready.pdf (7.21 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04183747 , version 1 (20-08-2023)



Robert van der Klis, Stephan Alaniz, Massimiliano Mancini, Cassio F. Dantas, Dino Ienco, et al.. PDiscoNet: Semantically consistent part discovery for fine-grained recognition. ICCV 2023 - International Conference on Computer Vision, Oct 2023, Paris, France. ⟨10.1109/ICCV51070.2023.00179⟩. ⟨hal-04183747⟩
150 View
68 Download



Gmail Facebook X LinkedIn More