Alternatives and similar repositories for lightly-train

Users that are interested in lightly-train are comparing it to the libraries listed below

• NVlabs / RADIO
  Official repository for "AM-RADIO: Reduce All Domains Into One"
  ☆1,329Updated this week
• yformer / EfficientTAM
  Efficient Track Anything
  ☆625Updated 7 months ago
• mhamilton723 / FeatUp
  Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024
  ☆1,572Updated last year
• facebookresearch / perception_models
  State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!
  ☆1,542Updated last week
• frank-xwang / UnSAM
  [NeurIPS 2024] Code release for "Segment Anything without Supervision"
  ☆480Updated 2 months ago
• tue-mps / eomt
  [CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).
  ☆331Updated last month
• ClaudiaCuttano / SAMWISE
  [CVPR25] Official repository for the paper: "SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation"
  ☆309Updated 2 months ago
• SkalskiP / top-cvpr-2025-papers
  About This repository is a curated collection of the most exciting and influential CVPR 2025 papers. 🔥 [Paper + Code + Demo]
  ☆768Updated 2 months ago
• voxel51 / fiftyone-brain
  Open source AI/ML capabilities for the FiftyOne ecosystem
  ☆146Updated this week
• IDEA-Research / DINO-X-API
  DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding
  ☆1,188Updated last month
• SkalskiP / top-cvpr-2024-papers
  This repository is a curated collection of the most exciting and influential CVPR 2024 papers. 🔥 [Paper + Code + Demo]
  ☆739Updated 3 months ago
• czg1225 / SlimSAM
  [NeurIPS 2024] SlimSAM: 0.1% Data Makes Segment Anything Slim
  ☆343Updated 6 months ago
• facebookresearch / hiera
  Hiera: A fast, powerful, and simple hierarchical vision transformer.
  ☆1,015Updated last year
• robustsam / RobustSAM
  RobustSAM: Segment Anything Robustly on Degraded Images (CVPR 2024 Highlight)
  ☆358Updated last year
• FocoosAI / focoos
  🚀 Lightning-fast computer vision models. Fine-tune SOTA models with just a few lines of code. Ready for cloud ☁️ and edge 📱 deployment.…
  ☆336Updated last week
• facebookresearch / dinov3
  Reference PyTorch implementation and models for DINOv3
  ☆6,102Updated 2 weeks ago
• jovanavidenovic / DAM4SAM
  [CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"
  ☆371Updated 2 months ago
• NVlabs / FasterViT
  [ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention
  ☆873Updated last month
• IDEA-Research / Grounding-DINO-1.5-API
  Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series
  ☆1,020Updated 7 months ago
• AssafSinger94 / dino-tracker
  Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)
  ☆505Updated 9 months ago
• Westlake-AGI-Lab / Distill-Any-Depth
  The repo for "Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator"
  ☆636Updated 4 months ago
• siyuanliii / masa
  Official Implementation of CVPR24 highlight paper: Matching Anything by Segmenting Anything
  ☆1,334Updated 4 months ago
• encord-team / encord-active
  The toolkit to test, validate, and evaluate your models and surface, curate, and prioritize the most valuable data for labeling.
  ☆452Updated 3 months ago
• zju3dv / MatchAnything
  Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.
  ☆1,088Updated last month
• UX-Decoder / DINOv
  [CVPR 2024] Official implementation of the paper "Visual In-context Learning"
  ☆490Updated last year
• voxel51 / fiftyone-plugins
  A curated list of plugins that you can add to your FiftyOne install!
  ☆131Updated this week
• heyoeyo / muggled_sam
  Muggled SAM: Segmentation without the magic
  ☆156Updated last week
• 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…
  ☆252Updated 2 years ago
• THU-MIG / yoloe
  YOLOE: Real-Time Seeing Anything [ICCV 2025]
  ☆1,659Updated 2 months ago
• niki-amini-naieni / CountGD
  Includes the code for training and testing the CountGD model from the paper CountGD: Multi-Modal Open-World Counting.
  ☆273Updated 2 months ago