Alternatives and similar repositories for SlimSAM

Users that are interested in SlimSAM are comparing it to the libraries listed below

• frank-xwang / UnSAM
  [NeurIPS 2024] Code release for "Segment Anything without Supervision"
  ☆495Updated last month
• robustsam / RobustSAM
  RobustSAM: Segment Anything Robustly on Degraded Images (CVPR 2024 Highlight)
  ☆364Updated last year
• hustvl / EVF-SAM
  Official code of "EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"
  ☆490Updated 9 months ago
• MaybeShewill-CV / segment-anything-u-specify
  using clip and sam to segment any instance you specify with text prompt of any instance names
  ☆182Updated 2 years ago
• xinghaochen / TinySAM
  [AAAI 2025] Official PyTorch implementation of "TinySAM: Pushing the Envelope for Efficient Segment Anything Model"
  ☆528Updated 11 months ago
• UX-Decoder / DINOv
  [CVPR 2024] Official implementation of the paper "Visual In-context Learning"
  ☆520Updated last year
• xushilin1 / RMP-SAM
  [ICLR 2025 oral] RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything
  ☆266Updated 8 months ago
• aim-uofa / Matcher
  [ICLR'24 & IJCV‘25] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
  ☆539Updated 3 weeks ago
• RockeyCoss / Prompt-Segment-Anything
  This is an implementation of zero-shot instance segmentation using Segment Anything.
  ☆317Updated 2 years ago
• czg1225 / Awesome-Efficient-Segment-Anything
  One summary of efficient segment anything models
  ☆112Updated last year
• SimonZeng7108 / efficientsam3
  ☆205Updated last week
• ylqi / Count-Anything
  This method uses Segment Anything and CLIP to ground and count any object that matches a custom text prompt, without requiring any point …
  ☆176Updated 2 years ago
• KBH00 / Semantic-Fast-SAM
  SSA + FastSAM/Semantic Fast Segment Anything , or Fast Semantic Segment Anything
  ☆114Updated 3 weeks ago
• baaivision / tokenize-anything
  [ECCV 2024] Tokenize Anything via Prompting
  ☆600Updated last year
• OPPOMKLab / recognize-anything
  Codebase for the Recognize Anything Model (RAM)
  ☆87Updated 2 years ago
• segments-ai / panoptic-segment-anything
  Combining Segment Anything (SAM) with Grounded DINO for zero-shot object detection and CLIPSeg for zero-shot segmentation
  ☆434Updated last year
• berkeley-hipie / HIPIE
  [NeurIPS2023] Code release for "Hierarchical Open-vocabulary Universal Image Segmentation"
  ☆292Updated 6 months ago
• Curt-Park / segment-anything-with-clip
  Segment Anything combined with CLIP
  ☆348Updated last year
• merveenoyan / siglip
  Projects based on SigLIP (Zhai et. al, 2023) and Hugging Face transformers integration 🤗
  ☆294Updated 10 months ago
• bytedance / coconut_cvpr2024
  ☆198Updated 7 months ago
• yformer / EfficientTAM
  Efficient Track Anything
  ☆757Updated 11 months ago
• tue-mps / eomt
  [CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).
  ☆506Updated 2 months ago
• autodistill / autodistill-grounded-sam-2
  Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.
  ☆134Updated last year
• hujiecpp / YOSO
  Code release for paper "You Only Segment Once: Towards Real-Time Panoptic Segmentation" [CVPR 2023]
  ☆285Updated 2 years ago
• bytedance / fc-clip
  [NeurIPS 2023] This repo contains the code for our paper Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convoluti…
  ☆333Updated last year
• naver-ai / ZIM
  [ICCV 2025, Highlight] ZIM: Zero-Shot Image Matting for Anything
  ☆385Updated 3 months ago
• ibaiGorordo / ONNX-SAM2-Segment-Anything
  Python scripts for the Segment Anythin 2 (SAM2) model in ONNX
  ☆281Updated last year
• uncbiag / SimpleClick
  SimpleClick: Interactive Image Segmentation with Simple Vision Transformers (ICCV 2023)
  ☆253Updated 4 months ago
• RobvanGastel / dinov3-finetune
  Testing adaptation of the DINOv2/3 encoders for vision tasks with Low-Rank Adaptation (LoRA)
  ☆394Updated 2 months ago
• alimohammadiamirhossein / smite
  Pytorch Implementation of "SMITE: Segment Me In TimE" (ICLR 2025)
  ☆212Updated last month