bbdamodaran

deepJDOT

Implementation of DeepJDOT in Keras

WAR

This repository contains the pytroch code to reproduce the results the paper "Wasserstein Adversarial Regularization for Learning with Label Noise"

AP_DERIVED

This repository contains the R codes of the Classification of Attribute profiles from the derived features for Urban cover classificationn

Allign_JDOT

Alligned Joint distribution optimal transport

gmllib

Machine Learning Library

HSIC_FS

This repository contains the matlab codes of Sparse HSIC Feature Selection Method

Adversarial-Example---FGSM

Crafting adversarial example for semantic segmentaion model using FGSM.

Autoencoder_NoisyLabels

This repository contains the code of supervised and unsupervised branch of autoencoder to avoid overfitting deep neural networks to the noisy labels

Awesome-Learning-with-Label-Noise

A curated list of resources for Learning with Noisy Labels

awesome-learning-with-noisy-labels

Related works for the learning with noisy labels

awesome-transfer-learning

Best transfer learning and domain adaptation resources (papers, tutorials, datasets, etc.)

CLEOT

Source code for the "Entropic optimal transport loss for learning deep neural networks under label noise"

Co-teaching

NIPS'18: Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels

Convolutional-Neural-Networks

Documents used to publish on Towards Data Science

coursera

da

domain adaption survey papers

ECCV-ALJDORT

keras-dl-benchmark

keras-resnet

Residual networks implementation using Keras-1.0 functional API

POT

Python Optimal Transport library

PRFF

This repository contains the codes of Pseudo Random Fourier Features for Approximating RBF kernel

Robust-Conditional-GAN

Code for reproducing results from our paper, Robustness of conditional GANs to noisy labels, NIPS 2018

sjdot

UBS_M2_DL

Materials for the deep learning course

VAT

Implementation of VAT (Virtual Adversarial Training) on keras.

woodyfeatures

This repository contains the R codes used for classification of woody features from pre-computed attribute profiles