AddaxAI — Peer-reviewed • Rank 7.5 • Science 100%

AddaxAI: A no-code platform to train and deploy custom YOLOv5 object detection models - Published in JOSS (2023)

OfflineMOT — Peer-reviewed • Rank 6.6 • Science 100%

OfflineMOT: A Python package for multiple objects detection and tracking from bird view stationary drone videos - Published in JOSS (2022)

Logodetect — Peer-reviewed • Rank 9.5 • Science 93%

Logodetect: One-shot detection of logos in image and video data - Published in JOSS (2022)

sahi • Rank 24.2 • Science 77%

Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

OmniTrax — Peer-reviewed • Rank 3.7 • Science 93%

OmniTrax: A deep learning-driven multi-animal tracking and pose-estimation add-on for Blender - Published in JOSS (2024)

ultralytics • Rank 31.9 • Science 64%

Ultralytics YOLO 🚀

albumentations • Rank 30.2 • Science 59%

Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

signature-lens • Rank 23.7 • Science 64%

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

mmdet3d • Rank 22.5 • Science 64%

OpenMMLab's next-generation platform for general 3D object detection.

rf-detr • Rank 20.7 • Science 64%

RF-DETR is a real-time object detection model architecture developed by Roboflow, SOTA on COCO and designed for fine-tuning.

supervision • Rank 29.2 • Science 54%

We write your reusable computer vision tools. 💜

inference • Rank 25.5 • Science 54%

Turn any computer or edge device into a command center for your computer vision projects.

catalyst • Rank 23.8 • Science 54%

Accelerated deep learning R&D

yolov3 • Rank 13.2 • Science 64%

YOLOv3 in PyTorch > ONNX > CoreML > TFLite

https://github.com/autogluon/autogluon • Rank 29.8 • Science 46%

Fast and Accurate ML in 3 Lines of Code

rastervision • Rank 21.4 • Science 54%

An open source library and framework for deep learning on satellite and aerial imagery.

avi-mmdet • Rank 29.1 • Science 46%

OpenMMLab Detection Toolbox and Benchmark

torchdistill • Rank 15.0 • Science 59%

A coding-free framework built on PyTorch for reproducible deep learning studies. PyTorch Ecosystem. 🏆26 knowledge distillation methods presented at CVPR, ICLR, ECCV, NeurIPS, ICCV, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.

mmdetection3d-note • Rank 7.8 • Science 64%

mmdetection3d 代码重点注解笔记

https://github.com/cheind/py-motmetrics • Rank 22.6 • Science 49%

:bar_chart: Benchmark multiple object trackers (MOT) in Python

mxnet.sharp • Rank 15.8 • Science 54%

.NET Standard bindings for Apache MxNet with Imperative, Symbolic and Gluon Interface for developing, training and deploying Machine Learning models in C#. https://mxnet.tech-quantum.com/

grad-cam • Rank 23.6 • Science 46%

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

geo-trax • Rank 2.1 • Science 67%

🚀 Geo-trax is a comprehensive pipeline for extracting and analyzing high-accuracy georeferenced vehicle trajectories from quasi-stationary, bird’s-eye view drone footage. Using advanced computer vision and deep learning, it enables detailed urban traffic analysis and supports scalable, precise studies of vehicle dynamics.

sc2-benchmark • Rank 4.1 • Science 64%

[TMLR] "SC2 Benchmark: Supervised Compression for Split Computing"

pylocron • Rank 10.6 • Science 54%

PyTorch implementations of recent Computer Vision tricks (ReXNet, RepVGG, Unet3p, YOLOv4, CIoU loss, AdaBelief, PolyLoss, MobileOne). Other additions: AdEMAMix

gluoncv • Rank 28.3 • Science 36%

Gluon CV Toolkit

autodistill • Rank 19.6 • Science 44%

Images to inference with no labeling (use foundation models to train supervised models).

cvat • Rank 15.2 • Science 46%

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

x-anylabeling • Rank 16.5 • Science 44%

Effortless data labeling with AI support from Segment Anything and other awesome models.

vitdet • Rank 6.4 • Science 54%

Unofficial implementation for [ECCV'22] "Exploring Plain Vision Transformer Backbones for Object Detection"

rf100-vl • Rank 5.7 • Science 54%

Code from the paper "Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models"

https://github.com/aim-uofa/adelaidet • Rank 11.7 • Science 46%

AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.

rasberry_perception • Rank 1.8 • Science 54%

General purpose ROS package for using deep learning/object detection frameworks on robots

musong • Rank 19.6 • Science 36%

Packaged version of ultralytics/yolov5 + many extra features

skellytracker • Rank 10.9 • Science 44%

A pose estimation and object detection/tracking backend for freemocap.

https://github.com/albumentations-team/albumentationsx • Rank 5.6 • Science 49%

Next-generation Albumentations: dual-licensed for open-source and commercial use

TACO • Rank 7.7 • Science 46%

🌮 Trash Annotations in Context Dataset Toolkit

yolo_ros • Rank 8.8 • Science 44%

Ultralytics YOLOv8, YOLOv9, YOLOv10, YOLOv11, YOLOv12 for ROS 2

hugsvision • Rank 6.1 • Science 46%

HugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision

targetran • Rank 7.9 • Science 44%

Python library for data augmentation in object detection or image classification model training

cppe5 • Rank 8.8 • Science 41%

Code for our paper CPPE - 5 (Medical Personal Protective Equipment), a new challenging object detection dataset

seglight • Rank 3.4 • Science 44%

Super fast and real-time semantic segmentation (cpu only) can be use for 1 core cpu

lrv-instruction • Rank 5.7 • Science 41%

[ICLR'24] Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning

VIAME • Rank 9.9 • Science 36%

Video and Image Analytics for Multiple Environments

kso • Rank 6.3 • Science 39%

Notebooks to upload/download marine footage, connect to a citizen science project, train machine learning models and publish marine biological observations.

mish • Rank 8.6 • Science 36%

Official Repository for "Mish: A Self Regularized Non-Monotonic Neural Activation Function" [BMVC 2020]

orca • Rank 0.0 • Science 44%

ORCA: Oceanic Recognition & Classification Application for sea-life analysis systems.

peoplesanspeople • Rank 7.7 • Science 36%

Unity's privacy-preserving human-centric synthetic data generator

promptdet • Rank 7.3 • Science 36%

PromptDet: Towards Open-vocabulary Detection using Uncurated Images, ECCV2022

snail-dataset • Rank 2.1 • Science 39%

detect-waste • Rank 7.8 • Science 33%

AI to Combat Environmental Pollution - detecting plastic waste in the environment to combat environmental pollution and promote circular economy (Deep Learning, PyTorch)

catnet • Rank 4.4 • Science 36%

🛰️ Learning to Aggregate Multi-Scale Context for Instance Segmentation in Remote Sensing Images (TNNLS 2024)

quickai • Rank 10.5 • Science 26%

QuickAI is a Python library that makes it extremely easy to experiment with state-of-the-art Machine Learning models.

mira • Rank 9.6 • Science 26%

Tooling for simple object detection projects

https://github.com/rybakov-ks/particleanalyzer • Rank 8.0 • Science 26%

A Computer Vision-based tool for automatic segmentation and size analysis of particles in Scanning Electron Microscope (SEM) images.

https://github.com/brainglobe/cellfinder-napari • Rank 10.5 • Science 23%

Efficient cell detection in large images using cellfinder in napari

https://github.com/amazon-science/bigdetection • Rank 7.4 • Science 23%

BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training

cube_detector • Rank 4.0 • Science 26%

Cube Detection using YOLOv5 with Oriented Bounding Boxes (OBB)

https://github.com/bencardoen/specht.jl • Rank 1.4 • Science 26%

SPECHT is a Julia implementation of a contrastive weakly supervised object detection and identification method for fluorescence microscopy.

https://github.com/alan-turing-institute/grace • Rank 6.6 • Science 20%

Graph Representation Analysis for Connected Embeddings

https://github.com/braun-steven/dafne • Rank 4.8 • Science 20%

Code for our paper "DAFNe: A One-Stage Anchor-Free Deep Model for Oriented Object Detection".

https://github.com/ammarlodhi255/crack-informed-yolov9-for-multi-locale-bone-fracture-detection • Rank 0.7 • Science 23%

This repository contains the implementation code of the paper "Small Data, Big Impact: A Multi-Locale Bone Fracture Detection on an Extremely Limited Dataset Via Crack-Informed YOLOv9 Variants"

https://github.com/broadinstitute/keras-rcnn • Rank 13.6 • Science 10%

Keras package for region-based convolutional neural networks (RCNNs)

https://github.com/autodistill/autodistill-owlv2 • Rank 7.7 • Science 13%

OWLv2 base model for use with Autodistill.

pyro-vision • Rank 10.3 • Science 10%

Computer vision library for wildfire detection 🌲 Deep learning models in PyTorch & ONNX for inference on edge devices (e.g. Raspberry Pi)

fastai • Rank 6.9 • Science 13%

R interface to fast.ai

https://github.com/autodistill/autodistill-transformers • Rank 3.4 • Science 13%

Use object detection models in Hugging Face Transformers to automatically label data to train a fine-tuned model.

Photovoltaic_Fault_Detector • Rank 5.9 • Science 10%

Model Photovoltaic Fault Detector based in model detector YOLOv.3, this repository contains four detector model with their weights and the explanation of how to use these models.

https://github.com/bencevans/megadetector-contained • Rank 1.1 • Science 13%

Docker image for running the MegaDetector v4 camera-trap object detection model.

https://github.com/nsembleai/nsvision • Rank 3.6 • Science 10%

nsvision is the image data pre and post processing and data augmentation library. It provides utilities for working with image data.

hbb2obb • Science 54%

📦 HBB2OBB is a Python library for converting horizontal (axis-aligned) bounding boxes to oriented (rotated) bounding boxes using SAM-based segmentation. Includes tools for visualization, evaluation, format conversion, and hyperparameter tuning.

trainyourownyolo • Science 49%

Train a state-of-the-art yolov3 object detector from scratch!

rl_drone_object_search • Science 57%

UAV-based path planning for efficient localization of non-uniformly distributed weeds using prior knowledge: A reinforcement-learning approach

https://github.com/bethgelab/siamese-mask-rcnn • Science 10%

Siamese Mask R-CNN model for one-shot instance segmentation

agml • Science 36%

AgML is a centralized framework for agricultural machine learning. AgML provides access to public agricultural datasets for common agricultural deep learning tasks, with standard benchmarks and pretrained models, as well the ability to generate synthetic data and annotations.

orientedformer • Science 49%

(TGRS 2024) OrientedFormer: An End-to-End Transformer-Based Oriented Object Detector in Remote Sensing Images

tardal • Science 36%

CVPR 2022 | Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection.

universenet • Science 54%

USB: Universal-Scale Object Detection Benchmark (BMVC 2022)

detection_inference • Science 54%

A high-performance, multi-threaded C++ pipeline for real-time multi-camera object detection using YOLOv8.

https://github.com/bitdessin/justdeepit • Science 39%

A tool with GUI and CUI for image analysis based on deep learning

yolic-labeling • Science 36%

The YOLIC Image Annotation Tool is a user-friendly software designed to support the You-Only-Look-at-Interested-Cells (YOLIC) methodology for real-time detection based on cell-wise segmentation.

sandi • Science 44%

Sediment ANalysis and Delineation through Images. A free and open-source software to process particles from high-resolution underwater images and to analyze gravels from laboratory images. Designed for contour detection, shape characterization and size measurement. SANDI is intended to become a collaborative project.

ai4rs • Science 44%

AI for remote sensing, remote sense, object detection, computer vision, cv

udmdet_tii • Science 67%

[TII 2024] An official implementation of ''A Novel Underwater Detection Method for Ambiguous Object Finding via Distraction Mining''

ParticleTracking — Peer-reviewed • Science 98%

ParticleTracking: A GUI and library for particle tracking on stereo camera images - Published in JOSS (2025)

steel-pipe-weld-defect-detection • Science 49%

Deep Learning Based Steel Pipe Weld Defect Detection

igarss-eq-object-detection-yolo-kahramanmaras • Science 67%

The study uses YOLO models on satellite imagery to detect collapsed buildings in Antakya after the 2023 Türkiye earthquake, achieving good results with YOLOv7 but highlighting challenges.

https://github.com/autodistill/autodistill-kosmos-2 • Science 13%

Kosmos-2 base model for use with Autodistill.

https://github.com/autodistill/autodistill-vlpart • Science 13%

VLPart model for use with Autodistill.

https://github.com/autodistill/autodistill-gpt-4v • Science 13%

GPT-4V(ision) module for use with Autodistill.

aodraw-mmdetection • Science 54%

(CVPR 2025 Highlight) Official repository of paper "AODRaw: Towards RAW Object Detection in Diverse Conditions" (https://arxiv.org/pdf/2411.15678)

yolov8-sheep-detection-counting • Science 26%

YOLOv8 Aerial Sheep Detection and Counting. Simulated on Gazebo.

ossid_code • Science 67%

Source code for OSSID: Online Self-Supervised Instance Detection by (And For) Pose Estimation

Lighter — Peer-reviewed • Science 93%

Lighter: Configuration-Driven Deep Learning - Published in JOSS (2025)

strip-r-cnn • Science 54%

Offical implementation of "Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection"

pix2seq • Science 67%

Simple Implementation of Pix2Seq model for object detection in PyTorch

mmrotate_rs • Science 26%

For Remote Sensing Object Detection & 2023df

https://github.com/atharvapathak/computer_vision_linear_regression_projects • Science 13%

This repository consists of some basic Computer Vision & Linear Regression Projects.

yogo • Science 44%

The "you only glance once" object detection model

sarlvision • Science 36%

A reinforcement learning object detector leveraging saliency ranking, offering a self-explainable system with a fully observable action log. | B.Sc. IT (Hons) Artificial Intelligence Dissertation | UOM Dean's List Awards 2024