DeepStream SDK Python bindings and sample applications

This repository offers a comprehensive collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-e…

A Unified Semi-Supervised Learning Codebase (NeurIPS'22)

streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL

[CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence

Visualize the low-level outputs of YOLOv8 to analyze and understand the areas where our model focuses. Specifically, illustrate which anchor points are activated to predict bounding boxes.

XAI for yoloV8

Wanna know what your model sees? Here's a package for applying EigenCAM and generating heatmap from the new YOLO V11 model

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

ROS2 Package to calculate the intrinsic and extrinsic camera calibration. Adding an easy way to fuse camera and lidars

TAO Toolkit deep learning networks with PyTorch backend

Curated list of project-based tutorials

Darknet/YOLO object detection framework

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

Replace 'hub' with 'ingest' in any github url to get a prompt-friendly extract of a codebase

This series will take you on a journey from the fundamentals of NLP and Computer Vision to the cutting edge of Vision-Language Models.

D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]

Dual Perspective Fusion Transformer for Camera-Radar-based Object Detection

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

This project implements Federated Learning using Flower. Clients train YOLOv8 locally, exchanging model parameters with the server. It orchestrates training, evaluation, and aggregation, ensuring c…

Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions [WACV 2023]

Unofficial Reimplementation of VLTSeg from "Strong but Simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning"

Official code of "EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"

Efficient Track Anything

Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation"

PyTorch code and models for the DINOv2 self-supervised learning method.

Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series

A high-performance C++ headers for real-time object detection and segmentation using YOLO models, leveraging ONNX Runtime and OpenCV for seamless integration. Supports multiple YOLO (v5, v7, v8, v9…