CLIP-Guided SAM: Parameter-Efficient Semantic Conditioning for Promptable Segmentation

• URL: http://arxiv.org/abs/2605.24807v1
• Date: Sun, 24 May 2026 01:40:30 GMT
• Title: CLIP-Guided SAM: Parameter-Efficient Semantic Conditioning for Promptable Segmentation
• Abstract summary: We propose CLIP-Guided SAM, a parameter-efficient segmentation framework built on internal semantic conditioning.<n>Instead of using semantic signals only to generate prompts, we inject CLIP-derived text, vision, and similarity features directly into SAM's image encoder.<n>Our framework is designed for low labeled-data settings and applies to both general-domain benchmarks and specialized downstream tasks.
• Score: 6.517222960194991
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 papers

• EOVSAM: Efficient Open-Vocabulary Segmentation with SAM 3 in One Pass [79.69317943751223]
  We propose an Efficient Open-Vocabulary segmentation framework with SAM 3 (EOVSAM)<n>EOVSAM adapts SAM 3 for single-pass prediction.<n>It consistently improves segmentation accuracy over vanilla SAM 3 on all evaluated datasets.
  arXiv  Detail & Related papers  (2026-08-03T14:15:37Z)
• Semantic-Fast-SAM: Efficient Semantic Segmenter [0.6816905600359814]
  We propose a semantic segmentation framework that combines the Fast Segment Anything model with a semantic labeling pipeline to achieve real-time performance without sacrificing accuracy.<n>FastSAM is an efficient CNN-based re-implementation of the Segment Anything Model (SAM) that runs much faster than the original transformer-based SAM.<n>SFS produces high-quality semantic segmentation maps at a fraction of the computational cost and memory footprint of the original SAM-based approach.
  arXiv  Detail & Related papers  (2026-04-22T04:18:39Z)
• Do Instance Priors Help Weakly Supervised Semantic Segmentation? [82.75875820720616]
  SeSAM is a framework that uses a foundational segmentation model, i.e. Segment Anything Model (SAM), with weak labels.<n>SeSAM decomposes class masks into connected components, samples point prompts along object skeletons, selects SAM masks using weak-label coverage, and iteratively refines labels using pseudo-labels.<n> integrated with a semi-supervised learning framework, SeSAM balances ground-truth labels, SAM-based pseudo-labels, and high-confidence pseudo-labels.
  arXiv  Detail & Related papers  (2026-04-13T08:29:49Z)
• SAM-PTx: Text-Guided Fine-Tuning of SAM with Parameter-Efficient, Parallel-Text Adapters [0.5755004576310334]
  This paper introduces SAM-PTx, a parameter-efficient approach for adapting SAM using frozen CLIP-derived text embeddings as class-level semantic guidance.<n>Specifically, we propose a lightweight adapter called Parallel-Text that injects text embeddings into SAM's image, enabling semantics-guided segmentation.<n>We show that incorporating fixed text embeddings as input improves segmentation performance over purely spatial prompt baselines.
  arXiv  Detail & Related papers  (2025-07-31T23:26:39Z)
• SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation [88.80792308991867]
  Segment Anything model (SAM) has shown ability to group image pixels into patches, but applying it to semantic-aware segmentation still faces major challenges.<n>This paper presents SAM-CP, a simple approach that establishes two types of composable prompts beyond SAM and composes them for versatile segmentation.<n> Experiments show that SAM-CP achieves semantic, instance, and panoptic segmentation in both open and closed domains.
  arXiv  Detail & Related papers  (2024-07-23T17:47:25Z)
• AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning [61.666973416903005]
  Segment Anything Model (SAM) has demonstrated its impressive generalization capabilities in open-world scenarios with the guidance of prompts. We propose a novel framework, termed AlignSAM, designed for automatic prompting for aligning SAM to an open context.
  arXiv  Detail & Related papers  (2024-06-01T16:21:39Z)
• Learning to Prompt Segment Anything Models [55.805816693815835]
  Segment Anything Models (SAMs) have demonstrated great potential in learning to segment anything. SAMs work with two types of prompts including spatial prompts (e.g., points) and semantic prompts (e.g., texts) We propose spatial-semantic prompt learning (SSPrompt) that learns effective semantic and spatial prompts for better SAMs.
  arXiv  Detail & Related papers  (2024-01-09T16:24:25Z)
• Stable Segment Anything Model [79.9005670886038]
  The Segment Anything Model (SAM) achieves remarkable promptable segmentation given high-quality prompts. This paper presents the first comprehensive analysis on SAM's segmentation stability across a diverse spectrum of prompt qualities. Our solution, termed Stable-SAM, offers several advantages: 1) improved SAM's segmentation stability across a wide range of prompt qualities, while 2) retaining SAM's powerful promptable segmentation efficiency and generality.
  arXiv  Detail & Related papers  (2023-11-27T12:51:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.