Context Label Learning: Improving Background Class Representations in Semantic Segmentation

TL;DR

This paper introduces CoLab, a method that decomposes the background class into subclasses using an auxiliary network, enhancing background representation and significantly improving semantic segmentation accuracy.

Contribution

The paper proposes a novel auxiliary network approach to automatically generate context labels, addressing background heterogeneity in segmentation tasks.

Findings

CoLab improves segmentation accuracy across multiple datasets.

It helps background logits stay away from decision boundaries.

Enhanced background class representation reduces over-segmentation.

Abstract

Background samples provide key contextual information for segmenting regions of interest (ROIs). However, they always cover a diverse set of structures, causing difficulties for the segmentation model to learn good decision boundaries with high sensitivity and precision. The issue concerns the highly heterogeneous nature of the background class, resulting in multi-modal distributions. Empirically, we find that neural networks trained with heterogeneous background struggle to map the corresponding contextual samples to compact clusters in feature space. As a result, the distribution over background logit activations may shift across the decision boundary, leading to systematic over-segmentation across different datasets and tasks. In this study, we propose context label learning (CoLab) to improve the context representations by decomposing the background class into several subclasses. Specifically, we train an auxiliary network as a task generator, along with the primary segmentation model, to automatically generate context labels that positively affect the ROI segmentation accuracy. Extensive experiments are conducted on several challenging segmentation tasks and datasets. The results demonstrate that CoLab can guide the segmentation model to map the logits of background samples away from the decision boundary, resulting in significantly improved segmentation accuracy. Code is available.