Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentation

TL;DR

This paper introduces a collaborative supervision approach for semi-supervised semantic segmentation that leverages both logit and representation spaces, improving robustness and training efficiency.

Contribution

It proposes a novel collaborative supervision method utilizing dual-space outputs and a new similarity indicator for better contrastive learning in semi-supervised segmentation.

Findings

Achieves competitive results on public benchmarks.

Reduces overfitting to incorrect semantic information.

Enhances knowledge exchange between logit and representation spaces.

Abstract

Semi-Supervised Semantic Segmentation (S4) aims to train a segmentation model with limited labeled images and a substantial volume of unlabeled images. To improve the robustness of representations, powerful methods introduce a pixel-wise contrastive learning approach in latent space (i.e., representation space) that aggregates the representations to their prototypes in a fully supervised manner. However, previous contrastive-based S4 methods merely rely on the supervision from the model's output (logits) in logit space during unlabeled training. In contrast, we utilize the outputs in both logit space and representation space to obtain supervision in a collaborative way. The supervision from two spaces plays two roles: 1) reduces the risk of over-fitting to incorrect semantic information in logits with the help of representations; 2) enhances the knowledge exchange between the two spaces. Furthermore, unlike previous approaches, we use the similarity between representations and prototypes as a new indicator to tilt training those under-performing representations and achieve a more efficient contrastive learning process. Results on two public benchmarks demonstrate the competitive performance of our method compared with state-of-the-art methods.