On Regularized Losses for Weakly-supervised CNN Segmentation

TL;DR

This paper introduces a novel approach to weakly-supervised CNN segmentation by integrating standard regularizers directly into loss functions, eliminating the need for explicit full mask generation and achieving state-of-the-art results.

Contribution

It proposes a new loss formulation that incorporates regularization directly, simplifying training and improving segmentation quality without extra inference steps.

Findings

Achieves state-of-the-art accuracy in weakly-supervised segmentation.

Outperforms methods relying on explicit mask generation.

Improves training efficiency and segmentation quality.

Abstract

Minimization of regularized losses is a principled approach to weak supervision well-established in deep learning, in general. However, it is largely overlooked in semantic segmentation currently dominated by methods mimicking full supervision via "fake" fully-labeled training masks (proposals) generated from available partial input. To obtain such full masks the typical methods explicitly use standard regularization techniques for "shallow" segmentation, e.g. graph cuts or dense CRFs. In contrast, we integrate such standard regularizers directly into the loss functions over partial input. This approach simplifies weakly-supervised training by avoiding extra MRF/CRF inference steps or layers explicitly generating full masks, while improving both the quality and efficiency of training. This paper proposes and experimentally compares different losses integrating MRF/CRF regularization terms. We juxtapose our regularized losses with earlier proposal-generation methods using explicit regularization steps or layers. Our approach achieves state-of-the-art accuracy in semantic segmentation with near full-supervision quality.