CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917626350927872 |
|---|---|
| author | Cho, Seokju Shin, Heeseong Hong, Sunghwan Arnab, Anurag Seo, Paul Hongsuck Kim, Seungryong |
| author_facet | Cho, Seokju Shin, Heeseong Hong, Sunghwan Arnab, Anurag Seo, Paul Hongsuck Kim, Seungryong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_11797 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation Cho, Seokju Shin, Heeseong Hong, Sunghwan Arnab, Anurag Seo, Paul Hongsuck Kim, Seungryong Computer Vision and Pattern Recognition 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. |
| title | CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2303.11797 |