Module of Axis-based Nexus Attention for weakly supervised object localization.

ABSTRACT: Weakly supervised object localization tasks remain challenging to identify and segment an entire object rather than only discriminative parts of the object. To tackle this problem, corruption-based approaches have been devised, which involve the training of non-discriminative regions by corrupting (e.g., erasing) the input images or intermediate feature maps. However, this approach requires an additional hyperparameter, the corrupting threshold, to determine the degree of corruption and can unfavorably disrupt training. It also tends to localize object regions coarsely. In this paper, we propose a novel approach, Module of Axis-based Nexus Attention (MoANA), which helps to adaptively activate less discriminative regions along with the class-discriminative regions without an additional hype

SUBMITTER: Sohn J 

PROVIDER: S-EPMC10616293 | biostudies-literature | 2023 Oct

REPOSITORIES: biostudies-literature