CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation

arXiv:2303.11797v2 Announce Type: replace
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 …

abstract adapt aggregation arxiv challenge clip cosine cost cs.cv foundation image labeling language novel pixel segmentation semantic text through type vision work