A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.

[Pedestron] Generalizable Pedestrian Detection: The Elephant In The Room. @ CVPR2021

Detectorch - detectron for PyTorch

RectLabel is an offline image annotation tool for object detection and segmentation.

Code for ICCV2019 paper "InstaBoost: Boosting Instance Segmentation Via Probability Map Guided Copy-Pasting"

[ECCV 2020] Boundary-preserving Mask R-CNN

A PyTorch Detectron codebase for domain adaptation of object detectors.

7th place solution for the 2018 Data Science Bowl with a score of 0.591

Chainer Implementation of Mask R-CNN. (Training code to reproduce the original result is available.)

Implements Adversarial Examples for Semantic Segmentation and Object Detection, using PyTorch and Detectron2

Domain Adaptive Faster R-CNN in Detectron

Real-time Detectron using webcam.

Epic Kitchens Object Detector and Feature Extractor using Faster-RCNN with Detectron2

Software to visualize detectron training stats

Detectron with VoVNet(CVPRW'19) backbone networks

Detectron with VoVNet : select the vovnet branch

AI Breast cancer detection using InBreast, CBIS-DDSM, MIAS mammography image datasets

Detectron is Facebook AI Research’s (FAIR) software system that implements state-of-the-art object detection algorithms, including Mask R-CNN. It is written in Python and powered by the Caffe2 deep learning framework. Detectron model is meant to advance object detection by offering speedy training and addressing the issues companies face when ma…

Object detection

The Jakarnotator is an annotation tool to create your own database for instance segmentation problem.