Foundation Model Assisted Weakly Supervised Semantic Segmentation

TL;DR

This paper introduces a novel framework leveraging foundation models CLIP and SAM to generate high-quality seeds for weakly supervised semantic segmentation, achieving state-of-the-art results on PASCAL VOC 2012.

Contribution

The work proposes a coarse-to-fine seed generation method using frozen foundation models with learnable prompts, improving weakly supervised segmentation performance.

Findings

Achieves state-of-the-art on PASCAL VOC 2012

Competitive results on MS COCO 2014

Effective seed generation with CLIP and SAM modules

Abstract

This work aims to leverage pre-trained foundation models, such as contrastive language-image pre-training (CLIP) and segment anything model (SAM), to address weakly supervised semantic segmentation (WSSS) using image-level labels. To this end, we propose a coarse-to-fine framework based on CLIP and SAM for generating high-quality segmentation seeds. Specifically, we construct an image classification task and a seed segmentation task, which are jointly performed by CLIP with frozen weights and two sets of learnable task-specific prompts. A SAM-based seeding (SAMS) module is designed and applied to each task to produce either coarse or fine seed maps. Moreover, we design a multi-label contrastive loss supervised by image-level labels and a CAM activation loss supervised by the generated coarse seed map. These losses are used to learn the prompts, which are the only parts need to be learned in our framework. Once the prompts are learned, we input each image along with the learned segmentation-specific prompts into CLIP and the SAMS module to produce high-quality segmentation seeds. These seeds serve as pseudo labels to train an off-the-shelf segmentation network like other two-stage WSSS methods. Experiments show that our method achieves the state-of-the-art performance on PASCAL VOC 2012 and competitive results on MS COCO 2014. Code is available at https://github.com/HAL-42/FMA-WSSS.git.