CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation
Abstract
Open-vocabulary semantic segmentation presents the challenge of labeling each pixel within an image based on a wide range of text descriptions. In this work we introduce a novel cost-based approach to adapt vision-language foundation models notably CLIP for the intricate task of semantic segmentation. Through aggregating the cosine similarity score i.e. the cost volume between image and text embeddings our method potently adapts CLIP for segmenting seen and unseen classes by fine-tuning its encoders addressing the challenges faced by existing methods in handling unseen classes. Building upon this we explore methods to effectively aggregate the cost volume considering its multi-modal nature of being established between image and text embeddings. Furthermore we examine various methods for efficiently fine-tuning CLIP.
Cite
Text
Cho et al. "CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation." Conference on Computer Vision and Pattern Recognition, 2024. doi:10.1109/CVPR52733.2024.00394Markdown
[Cho et al. "CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation." Conference on Computer Vision and Pattern Recognition, 2024.](https://mlanthology.org/cvpr/2024/cho2024cvpr-catseg/) doi:10.1109/CVPR52733.2024.00394BibTeX
@inproceedings{cho2024cvpr-catseg,
title = {{CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation}},
author = {Cho, Seokju and Shin, Heeseong and Hong, Sunghwan and Arnab, Anurag and Seo, Paul Hongsuck and Kim, Seungryong},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2024},
pages = {4113-4123},
doi = {10.1109/CVPR52733.2024.00394},
url = {https://mlanthology.org/cvpr/2024/cho2024cvpr-catseg/}
}