d-li14

HBONet

[ICCV 2019] Harmonious Bottleneck on Two Orthogonal Dimensions, surpassing MobileNetV2

involution

[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator

SAN

[ECCV 2020] Scale Adaptive Network: Learning to Learn Parameterized Classification Networks for Scalable Input Images

PSConv

[ECCV 2020] PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer

sequential-imagenet-dataloader

A plug-in replacement for DataLoader to load Imagenet disk-sequentially in PyTorch.

MetaNN

MetaModule provides extensions of PyTorch Module for meta learning

warpgrad

Meta-Learning with Warped Gradient Descent

DHM

[CVPR 2020] Dynamic Hierarchical Mimicking Towards Consistent Optimization Objectives

RPSnet

Official Implementation of "Random Path Selection for Incremental Learning" paper. NeurIPS 2019

learning-to-self-train

Learning to Self-Train for Semi-Supervised Few-Shot

Batch_Adaptive_Framework

An optimization framework that adapts the batch size in the process of training.

pytorch-meta

A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch

simple-blackbox-attack

Code for ICML 2019 paper "Simple Black-box Adversarial Attacks"

learn2learn

A PyTorch Library for Meta-learning Research

relu_networks_overconfident

Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem [CVPR 2019, oral]

cactus-maml

Code for Unsupervised Learning via Meta-Learning.

nettailor

Source code accompanying our CVPR 2019 paper: "NetTailor: Tuning the architecture, not just the weights."

ALiPy

ALiPy: Active Learning in Python is an active learning python toolbox, which allows users to conveniently evaluate, compare and analyze the performance of active learning methods.

meta-dataset

A dataset of datasets for learning to learn from few examples

Meta-RL

Implementation of Meta-RL A3C algorithm

dragonfly

An open source python library for scalable Bayesian optimisation.

foolbox

A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX

pixelRL

adversarial-robustness-toolbox

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

adversarial_image_defenses

Countering Adversarial Image using Input Transformations.

imitation

Code for the paper "Generative Adversarial Imitation Learning"

nasbot

Neural Architecture Search with Bayesian Optimisation and Optimal Transport

deep_architect_legacy

DeepArchitect: Automatically Designing and Training Deep Architectures

randomNAS_release

Code release for paper "Random Search and Reproducibility for NAS"

dissecting-reinforcement-learning

Python code, PDFs and resources for the series of posts on Reinforcement Learning which I published on my personal blog