CLIP-Guided SAM: Parameter-Efficient Semantic Conditioning for Promptable Segmentation
About
Promptable foundation models such as the Segment Anything Model (SAM) produce high-quality masks but remain semantically blind, relying on external prompts to specify categories. Existing vision-language approaches address this limitation by using external prompt coupling, where a vision-language model generates spatial prompts for SAM as a separate stage. We propose CLIP-Guided SAM, a parameter-efficient segmentation framework built on internal semantic conditioning. Instead of using semantic signals only to generate prompts, we inject CLIP-derived text, vision, and similarity features directly into SAM's image encoder through lightweight multi-modal semantic adapters. These adapters condition SAM's internal feature representations, allowing semantic information to influence mask prediction while preserving SAM's original promptable interface. Our framework is designed for low labeled-data settings and applies to both general-domain benchmarks and specialized downstream tasks. It supports two operating modes: Manual mode, for interactive segmentation with both text and spatial prompts, and Semi-Automatic text-only mode, for applications that require concept-specific segmentation using only textual input. We show that robustness depends on aligning training with the type of prompts used at inference, making train-test prompt consistency an important design principle. Through extensive experiments and ablations, we evaluate our method against SAM+PEFT baselines without semantic conditioning, vision-language + SAM pipelines, SAM 3, and strong semi-supervised segmentation methods that rely on large amounts of unlabeled data. Across these settings, CLIP-Guided SAM consistently achieves superior or competitive performance while remaining parameter-efficient in both training and deployment.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Camouflaged Object Detection | COD10K | -- | 217 | |
| Image Segmentation | COCO | mIoU69.2 | 39 | |
| Semantic segmentation | COCO | mIoU (1/512 ratio)60.5 | 15 | |
| Camouflaged Object Detection | CAMO | MAE0.044 | 6 | |
| Camouflaged Object Detection | Chameleon | MAE0.018 | 6 | |
| Semantic segmentation | PASCAL 1/16 | mIoU78.5 | 6 | |
| Semantic segmentation | ADE20K (1 64) | mIoU47.9 | 6 | |
| Semantic segmentation | ADE20K | mIoU (1/64)47.9 | 4 | |
| Semantic segmentation | Pascal VOC | mIoU (1/16)78.3 | 4 |