A patch-based architecture for multi-label classification from single label annotations
BUGEAU, Aurélie
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Institut universitaire de France [IUF]
See more >
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Institut universitaire de France [IUF]
BUGEAU, Aurélie
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Institut universitaire de France [IUF]
< Reduce
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Institut universitaire de France [IUF]
Language
en
Communication dans un congrès
This item was published in
International Conference on Computer Vision Theory and Applications (VISAPP'23), 2023-01-19, Lisbon. 2023
English Abstract
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 ...Read more >
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.Read less <
Origin
Hal imported