Bounding Box Tightness Prior for Weakly Supervised Image Segmentation

TL;DR

This paper introduces a novel weakly supervised image segmentation method using tight bounding box annotations, generalized multiple instance learning, and smooth maximum approximation to improve segmentation accuracy, especially in medical imaging.

Contribution

It proposes a new end-to-end deep learning approach that incorporates bounding box tightness priors via generalized MIL and smooth maximum functions, advancing weakly supervised segmentation.

Findings

Outperforms state-of-the-art methods on medical datasets.

Uses generalized MIL with crossing lines for positive bags.

Employs smooth maximum approximation to stabilize training.

Abstract

This paper presents a weakly supervised image segmentation method that adopts tight bounding box annotations. It proposes generalized multiple instance learning (MIL) and smooth maximum approximation to integrate the bounding box tightness prior into the deep neural network in an end-to-end manner. In generalized MIL, positive bags are defined by parallel crossing lines with a set of different angles, and negative bags are defined as individual pixels outside of any bounding boxes. Two variants of smooth maximum approximation, i.e., $\alpha$-softmax function and $\alpha$-quasimax function, are exploited to conquer the numeral instability introduced by maximum function of bag prediction. The proposed approach was evaluated on two pubic medical datasets using Dice coefficient. The results demonstrate that it outperforms the state-of-the-art methods. The codes are available at \url{https://github.com/wangjuan313/wsis-boundingbox}.