Min-max Entropy for Weakly Supervised Pointwise Localization

Belharbi Soufiane, Rony Jérôme, Dolz Jose, Ben Ayed Ismail, McCaffrey Luke, Granger Eric

Keywords: weakly supervised pointwise localization, deep learning, interpretability, computer vision

TL;DR: A deep learning method for weakly-supervised pointwise localization that learns using image-level label only. It relies on conditional entropy to localize relevant and irrelevant regions aiming to minimize false positive regions.

Abstract: Pointwise localization allows more precise localization and accurate interpretability, compared to bounding box, in applications where objects are highly unstructured such as in medical domain. In this work, we focus on weakly supervised localization (WSL) where a model is trained to classify an image and localize regions of interest at pixel-level using only global image annotation. Typical convolutional attentions maps are prune to high false positive regions. To alleviate this issue, we propose a new deep learning method for WSL, composed of a localizer and a classifier, where the localizer is constrained to determine relevant and irrelevant regions using conditional entropy (CE) with the aim to reduce false positive regions. Experimental results on a public medical dataset and two natural datasets, using Dice index, show that, compared to state of the art WSL methods, our proposal can provide significant improvements in terms of image-level classification and pixel-level localization (low false positive) with robustness to overfitting. A public reproducible PyTorch implementation is provided.

Code: https://drive.google.com/file/d/1qi2bjYq9jhL1H2D-zwtMl4X43viSDW7R/view?usp=sharing