A PyTorch Implementation of Feature Selective Anchor-Free Module for Single-Shot Object Detection (CVPR'19)
-
Updated
Nov 26, 2025 - Python
A PyTorch Implementation of Feature Selective Anchor-Free Module for Single-Shot Object Detection (CVPR'19)
Modern PyTorch toolkit for the VisDrone aerial object detection dataset with production-ready training pipelines, real-time inference, and format converters. Features state-of-the-art models (Faster R-CNN, FCOS, RetinaNet), mixed precision training, rich progress tracking, and optimizations for small object detection in drone imagery.
Deep Learning for Automatic Pneumonia Detection, RSNA challenge
[MICCAI 2024, top 11%] Official Pytorch implementation of Mammo-CLIP: A Vision Language Foundation Model to Enhance Data Efficiency and Robustness in Mammography
A Pythonic approach to object detection using Detectron2, a clean, modular framework for training and deploying computer vision models. DetectX simplifies the complexity of object detection while maintaining high performance and extensibility.
A simple and deeply commented PyTorch implementation of the RetinaNet paper, built as an educational resource. 📚 Demystify the core concepts of object detection with code that sticks closely to the original paper. 💡
This project is a part of my Multidisciplinary Project in semester 242 which aims to develop AI models for detecting diseases in bok choy plants. The project leverages deep learning techniques and distributed training to ensure scalability and efficiency.
RetinaNet-based AML and immune cell detection from multi-channel microscopy images.
This repository contains the deployment of a trained lung nodule detection model using YOLOv8 and RetinaNet architectures.
This is an object detection web app where users can upload an image, select a detection model, and view the processed image with detected objects. The result is downloadable for further use.
[Pedestron] Generalizable Pedestrian Detection: The Elephant In The Room. @ CVPR2021
RetinaNet for Object Detection
OpenMMLab Detection Toolbox and Benchmark
Official implementation of the papr 'A Study on Traffic Vulnerable Detection Using Object Detection-Based Esemble'
convert mmdetection model to tensorrt, support fp16, int8, batch input, dynamic shape etc.
It has never been rare among AI researchers that combine and evaluate different models to discover their methods. When I read about Retinanet and Efficientnet, I had a mind to combine them.
An (unofficial) implementation of Focal Loss, as described in the RetinaNet paper, generalized to the multi-class case.
Implementation of CVPR 2020 paper "EfficientDet: Scalable and Efficient Object Detection" using PyTorch and OpenCV
Official Detectron2 implementation of DA-RetinaNet, An unsupervised domain adaptation scheme for single-stage artwork recognition in cultural sites, Image and Vision Computing (IMAVIS) 2021
YOLO Series
Add a description, image, and links to the retinanet topic page so that developers can more easily learn about it.
To associate your repository with the retinanet topic, visit your repo's landing page and select "manage topics."