8000 Stars
Official Pytorch implementation of CutMix regularizer
Learning Meta Face Recognition in Unseen Domains, CVPR, Oral, 2020
D2-Net: A Trainable CNN for Joint Description and Detection of Local Features
Smooth Loss Functions for Deep Top-k Classification
SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.
Caffe implementation for Active Shift Layer(ASL)
Tensorflow implementation for Active Shift Layer(ASL)
DeepLab resnet v2 model in pytorch
PyTorch implementation of image classification models for CIFAR-10/CIFAR-100/MNIST/FashionMNIST/Kuzushiji-MNIST/ImageNet
Convert resnet trained in caffe to pytorch model. (group norm resnet is provided too)
Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset
Seed, Expand, Constrain: Three Principles for Weakly-Supervised Image Segmentation
Weakly 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).
Pytorch implementation of pyramidnet
Weakly Supervised Deep Detection Networks (CVPR 2016)
Weakly Supervised Object Localization with Progressive Domain Adaptation (CVPR 2016)
Implementation of Excitation Backprop in Caffe
MAttNet: Modular Attention Network for Referring Expression Comprehension
Code release for Hu et al. Natural Language Object Retrieval, in CVPR, 2016
Efficient Image Captioning code in Torch, runs on GPU
Unofficial pytorch implementation for Self-critical Sequence Training for Image Captioning. and others.
Pytorch code of for our CVPR 2018 paper "Neural Baby Talk"
Code release for Hu et al. Modeling Relationships in Referential Expressions with Compositional Modular Networks. in CVPR, 2017
Implementation of Grounding of Textual Phrases in Images by Reconstruction in Tensorflow
Implementation of Knowledge Aided Consistency for Weakly Supervised Phrase Grounding in Tensorflow
A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.
Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"
PyTorch implementation of two-stream networks for video action recognition
DeepArchitect: Automatically Designing and Training Deep Architectures
Referring expression comprehension on ReferIt(RefClef)