There are 12 repositories under detectron2 topic.
A Unified Toolkit for Deep Learning Based Document Image Analysis
A lightweight vision library for performing large scale object detection/ instance segmentation.
(CVPR 2021 Oral) Open World Object Detection
CenterMask : Real-time Anchor-Free Instance Segmentation, in CVPR 2020
This repo is implemented based on detectron2 and centernet
This is Pytorch re-implementation of our CVPR 2020 paper "Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation" (https://arxiv.org/abs/1911.10194)
Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [CVPR 2021]
VoVNet backbone networks for detectron2, in CVPR 2020
A PyTorch implementation of PointRend: Image Segmentation as Rendering
EntitySeg Toolbox: Towards Open-World and High-Quality Image Segmentation
SparseInst: Sparse Instance Activation for Real-Time Instance Segmentation, CVPR 2022
A PyTorch reimplementation of bottom-up-attention models
MPViT:Multi-Path Vision Transformer for Dense Prediction in CVPR 2022
Boundary-preserving Mask R-CNN (ECCV 2020)
detectron2 backbone: resnet18, efficientnet, hrnet, mobilenet v2, resnest, bifpn
Detectron2 for Document Layout Analysis
Instance segmentation for anime characters based on CondInst and SOLOv2
Repo for 42 days project to replicate/improve Airbnb's amenity (object) detection pipeline.
GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation. (CVPR 2021)
Conditional Convolutions for Instance Segmentation, achives 37.1mAP on coco val
Object Detection and Image Segmentation with Detectron2
Instance Shadow Detection (CVPR 2020)
Pytorch implementation of the paper, Neural re-rendering of humans from a single image.
YOLACT: Real-time Instance Segmentation on the FCOS detector (without bbox cropping), achives 35.2mAP on coco val
Learn how to train a custom instance segmentation model with Detectron2
Official code of ECCV 2020 paper "GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision". GSNet performs joint vehicle pose estimation and vehicle shape reconstruction with single RGB image as input.
Modular image processing pipeline using OpenCV and Python generators powered by Detectron2.
Cut out objects and remove backgrounds from pictures with artificial intelligence
This repository is the main Food Recognition Benchmark template and Starter kit. Clone the repository to compete now!
Matching Guided Distillation (ECCV 2020)
(TPAMI 2021) iOD: Incremental Object Detection via Meta-Learning
Official code of the paper "Expanding Low-Density Latent Regions for Open-Set Object Detection" (CVPR 2022)