Alternatives and similar repositories for UnSAM

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

• aim-uofa / Matcher
  [ICLR'24] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
  ☆500Updated 6 months ago
• hustvl / EVF-SAM
  Official code of "EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"
  ☆429Updated 3 months ago
• robustsam / RobustSAM
  RobustSAM: Segment Anything Robustly on Degraded Images (CVPR 2024 Highlight)
  ☆356Updated 10 months ago
• xushilin1 / RMP-SAM
  [ICLR 2025 oral] RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything
  ☆253Updated 3 months ago
• UX-Decoder / DINOv
  [CVPR 2024] Official implementation of the paper "Visual In-context Learning"
  ☆481Updated last year
• czg1225 / SlimSAM
  [NeurIPS 2024] SlimSAM: 0.1% Data Makes Segment Anything Slim
  ☆334Updated 4 months ago
• wysoczanska / clip_dinoiser
  Official implementation of 'CLIP-DINOiser: Teaching CLIP a few DINO tricks' paper.
  ☆249Updated 8 months ago
• NVlabs / RADIO
  Official repository for "AM-RADIO: Reduce All Domains Into One"
  ☆1,230Updated last week
• Jiawei-Yang / Denoising-ViT
  This is the official code release for our work, Denoising Vision Transformers.
  ☆369Updated 8 months ago
• u2seg / U2Seg
  [CVPR 2024] Code release for "Unsupervised Universal Image Segmentation"
  ☆208Updated last year
• berkeley-hipie / HIPIE
  [NeurIPS2023] Code release for "Hierarchical Open-vocabulary Universal Image Segmentation"
  ☆287Updated 3 weeks ago
• RobvanGastel / dinov2-finetune
  Testing adaptation of the DINOv2 encoder for vision tasks with Low-Rank Adaptation (LoRA)
  ☆151Updated 11 months ago
• bytedance / fc-clip
  [NeurIPS 2023] This repo contains the code for our paper Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convoluti…
  ☆321Updated last year
• tue-mps / eomt
  [CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).
  ☆247Updated last week
• baaivision / tokenize-anything
  [ECCV 2024] Tokenize Anything via Prompting
  ☆585Updated 7 months ago
• ByungKwanLee / Full-Segment-Anything
  This is Pytorch Implementation Code for adding new features in code of Segment-Anything. Here, the features support batch-input on the fu…
  ☆155Updated last year
• AssafSinger94 / dino-tracker
  Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)
  ☆494Updated 7 months ago
• itsprakhar / Downstream-Dinov2
  Downstream-Dino-V2: A GitHub repository featuring an easy-to-use implementation of the DINOv2 model by Facebook for downstream tasks such…
  ☆241Updated 2 years ago
• jovanavidenovic / DAM4SAM
  [CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"
  ☆344Updated 2 weeks ago
• bytedance / coconut_cvpr2024
  ☆186Updated last month
• MaybeShewill-CV / segment-anything-u-specify
  using clip and sam to segment any instance you specify with text prompt of any instance names
  ☆176Updated 2 years ago
• zamling / PSALM
  [ECCV2024] This is an official implementation for "PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model"
  ☆243Updated 6 months ago
• google / diffseg
  DiffSeg is an unsupervised zero-shot segmentation method using attention information from a stable-diffusion model. This repo implements …
  ☆316Updated last year
• syp2ysy / VRP-SAM
  [CVPR 2024] Official implementation of "VRP-SAM: SAM with Visual Reference Prompt"
  ☆147Updated 9 months ago
• Haiyang-W / GiT
  [ECCV2024 Oral🔥] Official Implementation of "GiT: Towards Generalist Vision Transformer through Universal Language Interface"
  ☆350Updated 5 months ago
• uncbiag / SimpleClick
  SimpleClick: Interactive Image Segmentation with Simple Vision Transformers (ICCV 2023)
  ☆239Updated this week
• segments-ai / panoptic-segment-anything
  Combining Segment Anything (SAM) with Grounded DINO for zero-shot object detection and CLIPSeg for zero-shot segmentation
  ☆419Updated last year
• heyoeyo / muggled_sam
  Muggled SAM: Segmentation without the magic
  ☆147Updated 3 months ago
• czg1225 / Awesome-Efficient-Segment-Anything
  One summary of efficient segment anything models
  ☆102Updated 11 months ago
• PengtaoJiang / Segment-Anything-CLIP
  Connecting segment-anything's output masks with the CLIP model; Awesome-Segment-Anything-Works
  ☆196Updated 9 months ago