Self-supervised Multi-scale Consistency for Weakly Supervised Segmentation Learning

TL;DR

This paper introduces a self-supervised multi-scale consistency loss with an attention mechanism to enhance weakly supervised segmentation, achieving state-of-the-art results on various datasets.

Contribution

It proposes a novel multi-scale consistency loss combined with attention to improve weakly supervised segmentation performance.

Findings

Achieves state-of-the-art results on multiple datasets.

Effectively leverages weak annotations like scribbles.

Improves segmentation accuracy with the proposed method.

Abstract

Collecting large-scale medical datasets with fine-grained annotations is time-consuming and requires experts. For this reason, weakly supervised learning aims at optimising machine learning models using weaker forms of annotations, such as scribbles, which are easier and faster to collect. Unfortunately, training with weak labels is challenging and needs regularisation. Herein, we introduce a novel self-supervised multi-scale consistency loss, which, coupled with an attention mechanism, encourages the segmentor to learn multi-scale relationships between objects and improves performance. We show state-of-the-art performance on several medical and non-medical datasets. The code used for the experiments is available at https://vios-s.github.io/multiscale-pyag.