CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation
This addresses the problem of pixel-level labeling with diverse text descriptions for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles open-vocabulary semantic segmentation by introducing a cost-based approach using CLIP, achieving effective segmentation for both seen and unseen classes through fine-tuning and cost aggregation.
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.