tianrun-chen/SAM-Adapter-PyTorch

Adapting Meta AI's Segment Anything to Downstream Tasks with Adapters and Prompts

What it solves

SAM-Adapter addresses the performance drops seen in the Segment Anything Model (SAM) when applied to challenging "underperformed scenes," such as camouflaged object detection, shadow detection, and medical image segmentation (e.g., polyp segmentation).

How it works

It adapts the pre-trained SAM backbone (supporting SAM, SAM2, and SAM3) to downstream tasks by incorporating an adapter mechanism. This allows the model to maintain the general segmentation capabilities of SAM while specializing in specific, difficult visual environments where the original model might fail.

Who it’s for

Computer vision researchers and developers working on specialized image segmentation tasks, particularly those involving low contrast, camouflage, or medical imaging.

Highlights

  • Support for SAM, SAM2, and SAM3 backbones.
  • Proven effectiveness on camouflaged object detection (COD10K, CAMO, CHAMELEON) and shadow detection (ISTD).
  • Applicable to medical imaging tasks like polyp segmentation (Kvasir dataset).
  • Provides configuration files for different ViT versions (ViT-H, ViT-L, ViT-B) to accommodate different GPU memory constraints.

Related

  • Project
    kadirnar/segment-anything-video

    A packaged version of the Segment Anything Model (SAM) that provides easy pip installation and extended support for video segmentation and cloud GPU integration.

  • Project
    yatengLG/ISAT_with_segment_anything

    An interactive semi-automatic image segmentation annotation tool that uses the Segment Anything Model (SAM) to accelerate the creation of labeled datasets.

  • Project
    computational-cell-analytics/micro-sam

    micro_sam is a napari‑based library that adapts Meta’s Segment Anything model for microscopy. It provides interactive 2‑D/3‑D segmentation and tracking with a few clicks, includes microscopy‑fine‑tuned SAM weights, and offers optional automatic prompt generation and lightweight fine‑tuning tools.

  • Project
    facebookresearch/sam3

    SAM 3 (Segment Anything with Concepts) is Meta’s 848 M‑parameter foundation model that lets you prompt an image or video with free‑form text (or visual exemplars) and receive masks, boxes, and scores for *all* matching objects. It combines a DETR‑style detector and a SAM 2‑style tracker, introduces a presence token for fine‑grained prompt discrimination, and is trained on >4 M auto‑annotated concepts. The repo provides installation steps, example notebooks, and a new SA‑CO benchmark (270 K concepts) for evaluation.

  • Project
    opengeos/segment-geospatial

    A Python package that adapts the Segment Anything Model (SAM) for geospatial data, enabling easy segmentation of satellite imagery using text, points, or boxes.