lightly-ai / lightly-trainLinks
All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
☆1,040Updated 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 repository for "AM-RADIO: Reduce All Domains Into One"☆1,376Updated 3 weeks ago
- Efficient Track Anything☆658Updated 10 months ago
- [CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).☆465Updated last week
- Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024☆1,596Updated last year
- [NeurIPS 2024] Code release for "Segment Anything without Supervision"☆487Updated last week
- [DEIMv2] Real Time Object Detection Meets DINOv3☆899Updated last week
- DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding☆1,272Updated 3 months ago
- [CVPR 2025 Highlight] Official repository for the paper: "SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation"☆334Updated last month
- RobustSAM: Segment Anything Robustly on Degraded Images (CVPR 2024 Highlight)☆361Updated last year
- Official Implementation of CVPR24 highlight paper: Matching Anything by Segmenting Anything☆1,347Updated 6 months ago
- Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series☆1,050Updated 9 months ago
- YOLOE: Real-Time Seeing Anything [ICCV 2025]☆1,876Updated 4 months ago
- Hiera: A fast, powerful, and simple hierarchical vision transformer.☆1,036Updated last year
- State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!☆1,718Updated last month
- Muggled SAM: Segmentation without the magic☆168Updated last week
- [CVPR 2024] Official implementation of the paper "Visual In-context Learning"☆511Updated last year
- [NeurIPS 2024] SlimSAM: 0.1% Data Makes Segment Anything Slim☆343Updated last month
- Includes the code for training and testing the CountGD model from the paper CountGD: Multi-Modal Open-World Counting.☆279Updated 4 months ago
- This repository is a curated collection of the most exciting and influential CVPR 2024 papers. 🔥 [Paper + Code + Demo]☆742Updated 5 months ago
- Open source AI/ML capabilities for the FiftyOne ecosystem☆151Updated this week
- [ICLR'24 & IJCV‘25] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching☆531Updated 10 months ago
- Testing adaptation of the DINOv2/3 encoders for vision tasks with Low-Rank Adaptation (LoRA)☆325Updated 2 weeks ago
- [CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"☆432Updated 2 weeks ago
- The repository provides code for training/fine tune the Meta Segment Anything Model 2 (SAM 2)☆271Updated last year
- Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)☆699Updated this week
- Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)☆528Updated 11 months ago
- Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.☆1,141Updated 3 months ago
- [ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention☆885Updated 3 months ago
- Downstream-Dino-V2: A GitHub repository featuring an easy-to-use implementation of the DINOv2 model by Facebook for downstream tasks such…☆263Updated 2 years ago
- SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation☆437Updated last week