Deep Vision

YOLOv4: Optimal Speed and Accuracy of Object Detection.

Detectron2 is FAIR's next-generation library that enables state-of-the-art computer vision research.

A popular and fast object detection model.

An open-source object detection toolbox based on PyTorch.

A framework for building and training object detection models in TensorFlow.

Implementation of Mask R-CNN, an algorithm for object instance segmentation.

FAIR's research platform for object detection research, implementing popular architectures like Faster R-CNN, Mask R-CNN, and Keypoint R-CNN.

The official implementation of S2ANet (Second-order Attention Network) for object detection.

Official YOLOv3 implementation.

ICCV 2015

ICCV 2015

Richard Zhang, Phillip Isola, Alexei A. Efros, ECCV, 2016

Deepak Pathak, Philipp Krahenbuhl, Jeff Donahue, Trevor Darrell, Alexei A. Efros, Context Encoders: Feature Learning by Inpainting, CVPR, 2016

Alexander Kolesnikov, Christoph Lampert, Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation, ECCV, 2016.

Matthrew Zeiler, Rob Fergus, Visualizing and Understanding Convolutional Networks, ECCV, 2014.

[[Paper]](https://www.cs.nyu.edu/~fergus/papers/zeilerECCV2014.pdf)

CVPR, 2015.

CVPR, 2015.

ICLR, 2015.

arXiv, 2015.

ECCV, 2014.

Junhua Mao, Wei Xu, Yi Yang, Jiang Wang, Zhiheng Huang, Alan L. Yuille, Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images, arXiv:1504.06692

Subhashini Venugopalan, Huijuan Xu, Jeff Donahue, Marcus Rohrbach, Raymond Mooney, Kate Saenko, Translating Videos to Natural Language Using Deep Recurrent Neural Networks, NAACL-HLT, 2015.

Xinlei Chen, C. Lawrence Zitnick, Learning a Recurrent Visual Representation for Image Caption Generation, arXiv:1411.5654.

CVPR, 2015.

arXiv:1410.1090.

arXiv:1411.2539.

arXiv:1411.4555.

CVPR 2015

CVPR, 2015.

arXiv:1502.03044 / ICML 2015

arXiv:1502.03671 / ICML 2015

arXiv:1504.06692

arXiv:1505.01809

arXiv:1506.01144

arXiv:1506.03694

arXiv:1508.02091

ICCV, 2015

Kelvin Xu, Jimmy Lei Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhutdinov, Richard S. Zemel, Yoshua Bengio, Show, Attend, and Tell: Neural Image Caption Generation with Visual Attention, arXiv:1502.03044 / ICML 2015

CVPR, 2015.

arXiv:1412.4729.

arXiv:1507.01053

arXiv:1505.01861.

arXiv:1505.00487.

arXiv:1502.08029

arXiv:1506.01698

arXiv:1506.06724

arXiv:1612.06950.

CVPR, 2015 SUNw:Scene Understanding workshop.

arXiv:1505.01121.

arXiv:1505.02074 / ICML 2015 deep learning workshop.

arXiv:1505.05612.

arXiv:1511.05765

arXiv:1511.02274.

arXiv:1603.01417 (2016).

arXiv01455

arXiv:1606.01847

arXiv:1606.03647

arXiv:1610.04325.

Aäron van den Oord, Nal Kalchbrenner, Oriol Vinyals, Lasse Espeholt, Alex Graves, Koray Kavukcuoglu. "Conditional Image Generation with PixelCNN Decoders"[[Paper]](https://arxiv.org/pdf/1606.05328v2.pdf)

Jun-Yan Zhu, Philipp Krahenbuhl, Eli Shechtman, and Alexei A. Efros, "Generative Visual Manipulation on the Natural Image Manifold", ECCV 2016. [Paper] [Video]

Artistic Style

Predicting Eye Fixations using Convolutional Neural Networks, CVPR, 2015.

Predicting Eye Fixations using Convolutional Neural Networks, CVPR, 2015.

Predicting Eye Fixations using Convolutional Neural Networks, CVPR, 2015.

Predicting Eye Fixations using Convolutional Neural Networks, NIPS, 2014.

The deep learning framework used for object detection and recognition.

CVPR, 2017.

ECCV, 2016.

NIPS, 2014.

Official implementation of Convolutional Pose Machines.

Official implementation of Stacked Hourglass Networks for human pose estimation.

Official implementation of Flowing ConvNets for human pose estimation in videos.

Deep Filter Banks for Texture Recognition and Segmentation, CVPR, 2015.

A practical and popular Python library for sequence labeling tasks.

A latent text-to-image diffusion model.

Latent diffusion models for high-resolution image synthesis.

Contrastive Language-Image Pre-training from OpenAI.

State-of-the-art Natural Language Processing for TensorFlow 2.x and PyTorch.

Unified Language Model Pre-training for Natural Language Understanding and Generation.

Bidirectional Encoder Representations from Transformers.

A PyTorch implementation of the Vision Transformer (ViT) model.

This repository provides examples of training deep learning models on NVIDIA GPUs.

Datasets, models, and transforms for computer vision in PyTorch.

A sequence modeling toolkit that allows researchers to train custom models for transcription and translation.

An open source machine learning framework for everyone.

Deep Learning for humans.

Tensors and Dynamic neural networks in Python with strong GPU acceleration.

A versatile Python library for implementing and training state-of-the-art computer vision models.

A library for deep 3D computer vision research, built off PyTorch.

Official PyTorch implementation of StyleGAN.

Official PyTorch implementation of StyleGAN2.

Official PyTorch implementation of StyleGAN3.

A PyTorch implementation of StyleGAN2.

Official implementation of the paper 'Self-Attention Generative Adversarial Networks'.

A PyTorch implementation of Self-Attention GAN.

A collection of Generative Adversarial Network implementations.

Official PyTorch implementation of StyleGAN2-ADA.

High-Resolution Image-to-Image Synthesis and Semantic Manipulation.

Official implementations of CycleGAN, pix2pix, and related image-to-image translation models.

Magenta is a research project by Google exploring the role of machine learning in creating art and music.

A repository containing PyTorch implementations of various adversarial attack methods against CNNs.

A toolkit for deep reinforcement learning, featuring implementations of popular algorithms.

OpenAI Baselines: reliable implementations of reinforcement learning algorithms.

Ray is a fast and simple framework for building distributed applications.

Parallel computing with Python.

Unified analytics engine for large-scale data processing.

Prometheus Helm charts maintained by the community.

The leading tool for visualizing, monitoring and discovering your metrics.

Open source, distributed, RESTful search and analytics engine.

An advanced log analysis tool based on deep learning.

A comprehensive dataset for log analysis.

A performance-focused cross platform machine learning inference and training accelerator.

An open deep learning compiler stack for CPUs, GPUs, and specialized accelerators.

A flexible, high-performance serving system for machine learning models, designed for production environments.

A flexible and easy-to-use tool for serving PyTorch models.

Open Neural Network Exchange format.

A dataset of millions of labeled images for object recognition.

A collection of datasets for image classification tasks (CIFAR-10, CIFAR-100).

Common Objects in Context dataset for object detection, segmentation, and captioning.

The largest publicly available dataset of image-text pairs.

A toolkit for experimenting with AI agents in the Doom game.

A toolkit for controlling agents in simulated physics environments.

A toolkit for developing and comparing reinforcement learning algorithms.

A PyTorch extension for distributed and mixed precision training.

A computer vision library for human-computer interaction based on CNNs