FfnFlood-Filling Networks for instance segmentation in 3d volumes.
D2detD2Det: Towards High Quality Object Detection and Instance Segmentation (CVPR2020)
AsisAssociatively Segmenting Instances and Semantics in Point Clouds, CVPR 2019
PaddledetectionObject Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
TfwssWeakly Supervised Segmentation with Tensorflow. Implements instance segmentation as described in Simple Does It: Weakly Supervised Instance and Semantic Segmentation, by Khoreva et al. (CVPR 2017).
Solov2SOLOv2: Dynamic, Faster and Stronger, achives 39.5mAP on coco test-dev (36 epochs result)
CiouComplete-IoU (CIoU) Loss and Cluster-NMS for Object Detection and Instance Segmentation (YOLACT)
KeraspersonlabKeras-tensorflow implementation of PersonLab (https://arxiv.org/abs/1803.08225)
AdelaidetAdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.
SoloSOLO: Segmenting Objects by Locations
TfvosSemi-Supervised Video Object Segmentation (VOS) with Tensorflow. Includes implementation of *MaskRNN: Instance Level Video Object Segmentation (NIPS 2017)* as part of the NIPS Paper Implementation Challenge.
Data science bowl 2018My 5th place (out of 816 teams) solution to The 2018 Data Science Bowl organized by Booz Allen Hamilton
Jsis3d[CVPR'19] JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds
Remo Python🐰 Python lib for remo - the app for annotations and images management in Computer Vision
Psconv[ECCV 2020] PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer
Copy Paste AugCopy-paste augmentation for segmentation and detection tasks
PazHierarchical perception library in Python for pose estimation, object detection, instance segmentation, keypoint estimation, face recognition, etc.
CountsegOfficial code for "Object counting and instance segmentation with image-level supervision", in CVPR 2019 and TPAMI 2020
Deepco3[CVPR19] DeepCO3: Deep Instance Co-segmentation by Co-peak Search and Co-saliency (Oral paper)
Mask rcnn pytorchMask R-CNN for object detection and instance segmentation on Pytorch
Ac FpnImplement of paper 《Attention-guided Context Feature Pyramid Network for Object Detection》
Bmaskr CnnBoundary-preserving Mask R-CNN (ECCV 2020)
Lanenet Lane DetectionUnofficial implemention of lanenet model for real time lane detection using deep neural network model https://maybeshewill-cv.github.io/lanenet-lane-detection/
CondinstConditional Convolutions for Instance Segmentation, achives 37.1mAP on coco val
PanetPANet for Instance Segmentation and Object Detection
Maskrcnn ModanetA Mask R-CNN Keras implementation with Modanet annotations on the Paperdoll dataset
Data Science Bowl 2018End-to-end one-class instance segmentation based on U-Net architecture for Data Science Bowl 2018 in Kaggle
Yolact fcosYOLACT: Real-time Instance Segmentation on the FCOS detector (without bbox cropping), achives 35.2mAP on coco val
SoloSOLO and SOLOv2 for instance segmentation, ECCV 2020 & NeurIPS 2020.
GcnetGCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
AcisActor-Critic Instance Segmentation (CVPR 2019)
Cell DetrOfficial and maintained implementation of the paper Attention-Based Transformers for Instance Segmentation of Cells in Microstructures [BIBM 2020].
LabelmeImage Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
Polyrnn PpInference Code for Polygon-RNN++ (CVPR 2018)
Yolact edgeThe first competitive instance segmentation approach that runs on small edge devices at real-time speeds.
CentermaskCenterMask : Real-Time Anchor-Free Instance Segmentation, in CVPR 2020
Centermask2Real-time Anchor-Free Instance Segmentation, in CVPR 2020
UpsnetUPSNet: A Unified Panoptic Segmentation Network
Mask rcnnMask R-CNN for object detection and instance segmentation on Keras and TensorFlow
YolactA simple, fully convolutional model for real-time instance segmentation.
Panoptic DeeplabThis 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)
PixellibVisit PixelLib's official documentation https://pixellib.readthedocs.io/en/latest/
Involution[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator