A patch-based architecture for multi-label classification from single label annotations - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

A patch-based architecture for multi-label classification from single label annotations

Résumé

In this paper, we propose a patch-based architecture for multi-label classification problems where only a single positive label is observed in images of the dataset. Our contributions are twofold. First, we introduce a light patch architecture based on the attention mechanism. Next, leveraging on patch embedding self-similarities, we provide a novel strategy for estimating negative examples and deal with positive and unlabeled learning problems. Experiments demonstrate that our architecture can be trained from scratch, whereas pre-training on similar databases is required for related methods from the literature.

Dates et versions

hal-03783915 , version 1 (22-09-2022)

Identifiants

Citer

Warren Jouanneau, Aurélie Bugeau, Marc Palyart, Nicolas Papadakis, Laurent Vézard. A patch-based architecture for multi-label classification from single label annotations. International Conference on Computer Vision Theory and Applications (VISAPP'23), Jan 2023, Lisbon, Portugal. ⟨hal-03783915⟩

Collections

CNRS
42 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More