LAVIS - A One-stop Library for Language-Vision Intelligence

A new framework for open-vocabulary object detection, based on maskrcnn-benchmark

End-to-End Object Detection with Transformers

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

Grid features pre-training code for visual question answering

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

Models and examples built with TensorFlow

BISON: Binary Image SelectiON

Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version

PyTorch source code for "Stacked Cross Attention for Image-Text Matching"

COCO API - Dataset @ http://cocodataset.org/

Caffe: a fast open framework for deep learning.

Efficient, transparent deep learning in hundreds of lines of code.

Convolutional Neural Networks