Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation

TL;DR

SemPLeS introduces a novel prompt learning framework that leverages CLIP's latent space to improve semantic alignment in weakly-supervised segmentation, leading to more accurate pseudo masks and better performance on benchmarks.

Contribution

The paper proposes a new Semantic Prompt Learning framework that enhances WSSS by learning prompts to better align segmented regions with object categories using CLIP.

Findings

Achieves competitive results on PASCAL VOC 2012 and MS COCO 2014.

Effectively suppresses co-occurring backgrounds in pseudo masks.

Compatible with existing WSSS methods.

Abstract

Weakly-Supervised Semantic Segmentation (WSSS) aims to train segmentation models using image data with only image-level supervision. Since precise pixel-level annotations are not accessible, existing methods typically focus on producing pseudo masks for training segmentation models by refining CAM-like heatmaps. However, the produced heatmaps may capture only the discriminative image regions of object categories or the associated co-occurring backgrounds. To address the issues, we propose a Semantic Prompt Learning for WSSS (SemPLeS) framework, which learns to effectively prompt the CLIP latent space to enhance the semantic alignment between the segmented regions and the target object categories. More specifically, we propose Contrastive Prompt Learning and Prompt-guided Semantic Refinement to learn the prompts that adequately describe and suppress the co-occurring backgrounds associated with each object category. In this way, SemPLeS can perform better semantic alignment between object regions and class labels, resulting in desired pseudo masks for training segmentation models. The proposed SemPLeS framework achieves competitive performance on standard WSSS benchmarks, PASCAL VOC 2012 and MS COCO 2014, and shows compatibility with other WSSS methods. Code: https://github.com/NVlabs/SemPLeS.