EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model
This work addresses the limitation of SAM in handling text prompts for referring segmentation, offering a more efficient and accurate solution for vision-language tasks, though it is incremental as it builds on existing models like SAM and BEIT-3.
The paper tackles the problem of adapting the Segment Anything Model (SAM) for text-prompted referring expression segmentation by introducing EVF-SAM, which uses early vision-language fusion and multimodal prompts, achieving state-of-the-art performance on RefCOCO/+/g datasets with 1.32B parameters and an 82% reduction in parameters compared to previous methods.
Segment Anything Model (SAM) has attracted widespread attention for its superior interactive segmentation capabilities with visual prompts while lacking further exploration of text prompts. In this paper, we empirically investigate what text prompt encoders (e.g., CLIP or LLM) are good for adapting SAM for referring expression segmentation and introduce the Early Vision-language Fusion-based SAM (EVF-SAM). EVF-SAM is a simple yet effective referring segmentation method which exploits multimodal prompts (i.e., image and text) and comprises a pre-trained vision-language model to generate referring prompts and a SAM model for segmentation. Surprisingly, we observe that: (1) multimodal prompts and (2) vision-language models with early fusion (e.g., BEIT-3) are beneficial for prompting SAM for accurate referring segmentation. Our experiments show that the proposed EVF-SAM based on BEIT-3 can obtain state-of-the-art performance on RefCOCO/+/g for referring expression segmentation and demonstrate the superiority of prompting SAM with early vision-language fusion. In addition, the proposed EVF-SAM with 1.32B parameters achieves remarkably higher performance while reducing nearly 82% of parameters compared to previous SAM methods based on large multimodal models.