Alternatives and similar repositories for Semantic-Fast-SAM

Users that are interested in Semantic-Fast-SAM are comparing it to the libraries listed below

• xushilin1 / RMP-SAM
  [ICLR 2025 oral] RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything
  ☆259Updated 4 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
  ☆176Updated 2 years ago
• Curt-Park / yolo-world-with-efficientvit-sam
  YOLO-World + EfficientViT SAM
  ☆103Updated last year
• akashAD98 / YOLOV8_SAM
  yolov8 model with SAM meta
  ☆140Updated last year
• hujiecpp / YOSO
  Code release for paper "You Only Segment Once: Towards Real-Time Panoptic Segmentation" [CVPR 2023]
  ☆277Updated 2 years ago
• GuoleiSun / Awesome-SAM2
  This repo aims to include materials (papers, codes, slides) about SAM2 (segment anything in images and videos). We are continuously impro…
  ☆98Updated 2 weeks ago
• fanq15 / Stable-SAM
  ☆70Updated last year
• OPPOMKLab / recognize-anything
  Codebase for the Recognize Anything Model (RAM)
  ☆82Updated last year
• 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 …
  ☆169Updated 2 years ago
• sajjad-sh33 / ViT-P
  The Missing Point in Vision Transformers for Universal Image Segmentation
  ☆50Updated 2 months ago
• luckybird1994 / ASAM
  ☆93Updated last year
• ymgw55 / segment-anything-edge-detection
  Unofficial edge detection implementation using the Automatic Mask Generation (AMG) of the Segment Anything Model (SAM).
  ☆74Updated 2 months ago
• PengtaoJiang / Segment-Anything-CLIP
  Connecting segment-anything's output masks with the CLIP model; Awesome-Segment-Anything-Works
  ☆196Updated 10 months ago
• czg1225 / SlimSAM
  [NeurIPS 2024] SlimSAM: 0.1% Data Makes Segment Anything Slim
  ☆340Updated 6 months ago
• wanghao9610 / X-SAM
  X-SAM: From Segment Anything to Any Segmentation
  ☆171Updated last week
• autodistill / autodistill-grounded-sam-2
  Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.
  ☆127Updated last year
• weihao1115 / mm-sam
  The official implementation of "Segment Anything with Multiple Modalities".
  ☆100Updated 11 months ago
• IRVLUTD / NIDS-Net
  [IROS 2025] NIDS-Net: A unified framework for novel instance detection and segmentation
  ☆67Updated 3 months ago
• zhang-tao-whu / DVIS
  DVIS: Decoupled Video Instance Segmentation Framework
  ☆152Updated last year
• niki-amini-naieni / CountVid
  Includes the VideoCount dataset and CountVid code for the paper Open-World Object Counting in Videos.
  ☆66Updated last month
• fudan-zvg / meta-prompts
  ☆73Updated 6 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…
  ☆248Updated 2 years ago
• zhang-tao-whu / DVIS_Plus
  ☆125Updated last year
• uncbiag / SegNext
  Rethinking Interactive Image Segmentation with Low Latency, High Quality, and Diverse Prompts (CVPR 2024)
  ☆95Updated 3 weeks ago
• jvpassarelli / sam-clip-segmentation
  Image Instance Segmentation - Zero Shot - OpenAI's CLIP + Meta's SAM
  ☆71Updated 2 years ago
• frank-xwang / UnSAM
  [NeurIPS 2024] Code release for "Segment Anything without Supervision"
  ☆480Updated 2 months ago
• 983632847 / SAM-for-Videos
  This repository is for the first survey on SAM & SAM2 for Videos.
  ☆52Updated 3 months ago
• zshn25 / DINOv2_mmseg
  Training and testing of DINOv2 for segmentation downstream
  ☆39Updated 6 months ago
• segments-ai / panoptic-segment-anything
  Combining Segment Anything (SAM) with Grounded DINO for zero-shot object detection and CLIPSeg for zero-shot segmentation
  ☆422Updated last year
• ragavsachdeva / The-Change-You-Want-to-See
  The official implementation of the paper The Change You Want to See (WACV 2023).
  ☆64Updated last year