OpenMMLab Detection Toolbox and Benchmark

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

We write your reusable computer vision tools. 💜

A simple, fully convolutional model for real-time instance segmentation.

🛰️ List of satellite image training datasets with annotations for computer vision and deep learning

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

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

🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

A Simple and Versatile Framework for Object Detection and Instance Recognition

Unofficial implemention of lanenet model for real time lane detection

SOLO and SOLOv2 for instance segmentation, ECCV 2020 & NeurIPS 2020.

🔥[IEEE TPAMI 2020] Deep Learning for 3D Point Clouds: A Survey

[CVPR'23] Universal Instance Perception as Object Discovery and Retrieval

[ICLR'23 Spotlight🔥] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"

PANet for Instance Segmentation and Object Detection

[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator

The first competitive instance segmentation approach that runs on small edge devices at real-time speeds.

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