English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Fine-grained classification often requires recognizing specific object parts,such as beak shape and wing patterns for birds. Encouraging a fine-grainedclassification model to first detect such parts and then using them to inferthe class could help us gauge whether the model is indeed looking at the rightdetails better than with interpretability methods that provide a singleattribution map. We propose PDiscoNet to discover object parts by using onlyimage-level class labels along with priors encouraging the parts to be:discriminative, compact, distinct from each other, equivariant to rigidtransforms, and active in at least some of the images. In addition to using theappropriate losses to encode these priors, we propose to use part-dropout,where full part feature vectors are dropped at once to prevent a single partfrom dominating in the classification, and part feature vector modulation,which makes the information coming from each part distinct from the perspectiveof the classifier. Our results on CUB, CelebA, and PartImageNet show that theproposed method provides substantially better part discovery performance thanprevious methods while not requiring any additional hyper-parameter tuning andwithout penalizing the classification performance. The code is available athttps://github.com/robertdvdk/part_detection.

PDiscoNet: Semantically consistent part discovery for fine-grained recognition