lightly-ai / lightly-trainLinks
All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
☆925Updated last week
Alternatives and similar repositories for lightly-train
Users that are interested in lightly-train are comparing it to the libraries listed below
Sorting:
- Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024☆1,589Updated last year
- Efficient Track Anything☆650Updated 9 months ago
- [CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).☆416Updated 3 weeks ago
- Official repository for "AM-RADIO: Reduce All Domains Into One"☆1,356Updated 3 weeks ago
- [NeurIPS 2024] Code release for "Segment Anything without Supervision"☆484Updated last month
- DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding☆1,241Updated 2 months ago
- [DEIMv2] Real Time Object Detection Meets DINOv3☆639Updated this week
- Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series☆1,043Updated 8 months ago
- State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!☆1,659Updated last month
- Hiera: A fast, powerful, and simple hierarchical vision transformer.☆1,025Updated last year
- RobustSAM: Segment Anything Robustly on Degraded Images (CVPR 2024 Highlight)☆360Updated last year
- [CVPR 2025 Highlight] Official repository for the paper: "SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation"☆327Updated 3 weeks ago
- This repository is a curated collection of the most exciting and influential CVPR 2024 papers. 🔥 [Paper + Code + Demo]☆740Updated 4 months ago
- About This repository is a curated collection of the most exciting and influential CVPR 2025 papers. 🔥 [Paper + Code + Demo]☆788Updated 4 months ago
- Official Implementation of CVPR24 highlight paper: Matching Anything by Segmenting Anything☆1,346Updated 5 months ago
- The repository provides code for training/fine tune the Meta Segment Anything Model 2 (SAM 2)☆264Updated last year
- [ICLR'24 & IJCV‘25] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching☆521Updated 10 months ago
- [ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention☆881Updated 2 months ago
- Open source AI/ML capabilities for the FiftyOne ecosystem☆147Updated last month
- Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)☆523Updated 10 months ago
- Testing adaptation of the DINOv2/3 encoders for vision tasks with Low-Rank Adaptation (LoRA)☆280Updated last week
- Includes the code for training and testing the CountGD model from the paper CountGD: Multi-Modal Open-World Counting.☆278Updated 3 months ago
- YOLOE: Real-Time Seeing Anything [ICCV 2025]☆1,821Updated 3 months ago
- [NeurIPS 2024] SlimSAM: 0.1% Data Makes Segment Anything Slim☆344Updated 2 weeks ago
- Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupe…☆1,036Updated 4 months ago
- [CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"☆421Updated 2 weeks ago
- [CVPR 2024] Official implementation of the paper "Visual In-context Learning"☆504Updated last year
- Downstream-Dino-V2: A GitHub repository featuring an easy-to-use implementation of the DINOv2 model by Facebook for downstream tasks such…☆262Updated 2 years ago
- Muggled SAM: Segmentation without the magic☆165Updated last month
- ☆62Updated last year