Semantic Prompt Learning for
Weakly-Supervised Semantic Segmentation

WACV 2025

Ci-Siang Lin1,2* Chien-Yi Wang2 Yu-Chiang Frank Wang1,2 Min-Hung Chen2$\dagger$
1Graduate Institute of Communication Engineering, National Taiwan University, Taiwan 2NVIDIA
* Work done during an internship at NVIDIA $\dagger$ Project Lead
arXiv

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.

Proposed Method

An overview of our proposed SemPLeS framework. We first introduce (a) Segment-Label Matching, which leverages image-text contrastive learning to train the mask generator $S$ and produce initial object masks $M$. Such derived masks are still coarse and may falsely include co-occurring backgrounds. To achieve class-associated mask refinement and produce the refined mask $M'$, we propose (b) Contrastive Prompt Learning to automatically learn prompts $p_k$ embedded with semantic knowledge from the CLIP latent space, followed by (c) Prompt-guided Semantic Refinement to suppress co-occurring backgrounds associated with each category $k$.

Experiments

Quantitative Comparisons

Quantitative results of segmentation masks on PASCAL VOC 2012 [20] val and test sets. “Backbone” denotes the segmentation network. “DL”, “Res”, “WRes”, and “M2F” denote DeepLab [6], ResNet [23], WideResNet [74], and Mask2Former [15], respectively.

Quantitative results of the segmentation masks on MS COCO 2014 [41] val set.

Qualitative Comparisons

Qualitative results of CAMs. “GT” denotes the ground truth masks. We see that our proposed SemPLeS framework produces precise CAMs better aligned with the ground truth masks.

Qualitative results of segmentation maps. “GT” denotes the ground truth masks.

BibTeX

If you find this useful for your research, please consider citing: 
@article{lin2024semples,
  title={SemPLeS: Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation},
  author={Lin, Ci-Siang and Wang, Chien-Yi and Wang, Yu-Chiang Frank and Chen, Min-Hung},
  journal={arXiv preprint arXiv:2401.11791},
  year={2024}
}