kgl-prml's repositories
Contrastive-Adaptation-Network-for-Unsupervised-Domain-Adaptation
pytorch implementation for Contrastive Adaptation Network
Pixel-Level-Cycle-Association
Pytorch Implementation for NeurIPS (oral) paper: Pixel Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation
shakeout-for-caffe
Shakeout: A New Approach to Regularized Deep Neural Network Training
DeepVideoAnalytics
Analyze videos & images, perform detections, index frames & detected objects, search by examples.
EventMaskTrain
The training code for generating event masks
evolution-strategies-starter
Starter code for Evolution Strategies
AmazingTransferLearning
Transfer Learning, Domain Adaptation
atari_multitask
Atari gauntlet for RL agents
awesome-action-recognition
A curated list of action recognition and related area resources
awesome-semantic-segmentation
awesome-semantic-segmentation
caffe-model
Caffe models (imagenet pretrain) and prototxt generator scripts for inception_v3 \ inception_v4 \ inception_resnet \ fractalnet \ resnext
capsule-net-pytorch
A PyTorch implementation of CapsNet architecture in the NIPS 2017 paper "Dynamic Routing Between Capsules".
DBPN-Pytorch
Deep Back-Projection Networks for Super-Resolution
dircolors-solarized
This is a repository of themes for GNU ls (configured via GNU dircolors) that support Ethan Schoonover’s Solarized color scheme.
fashion-mnist
A MNIST-like fashion product database. Benchmark :point_right:
functional-zoo
PyTorch and Tensorflow functional model definitions
Imagenet32_Scripts
Scripts for Imagenet 32 dataset
pytorch-explain-black-box
PyTorch implementation of Interpretable Explanations of Black Boxes by Meaningful Perturbation
Relation-Networks-for-Object-Detection
Relation Networks for Object Detection
rl-teacher
Code for Deep RL from Human Preferences [Christiano et al]. Plus a webapp for collecting human feedback
super-events-cvpr18
Code for our CVPR 2018 paper "Learning Latent Super-Events to Detect Multiple Activities in Videos"
youtube-8m
Starter code for working with the YouTube-8M dataset.