Improving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Label

arXiv:2404.09475v1 Announce Type: new
Abstract: Weakly-supervised learning approaches have gained significant attention due to their ability to reduce the effort required for human annotations in training neural networks. This paper investigates a framework for weakly-supervised object localization, which aims to train a neural network capable of predicting both the object class and its location using only images and their image-level class labels. The proposed framework consists of a shared feature extractor, a classifier, and a localizer. The localizer predicts pixel-level …

abstract adversarial annotations arxiv attention cs.ai cs.cv framework human improving localization network networks neural network neural networks object paper reduce supervised learning train training type weakly-supervised