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

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

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

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

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

MetaModule provides extensions of PyTorch Module for meta learning

Meta-Learning with Warped Gradient Descent

[CVPR 2020] Dynamic Hierarchical Mimicking Towards Consistent Optimization Objectives

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

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

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

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

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

A PyTorch Library for Meta-learning Research

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

Code for Unsupervised Learning via Meta-Learning.

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

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.

A dataset of datasets for learning to learn from few examples

Implementation of Meta-RL A3C algorithm

An open source python library for scalable Bayesian optimisation.

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

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

Countering Adversarial Image using Input Transformations.

Code for the paper "Generative Adversarial Imitation Learning"

Neural Architecture Search with Bayesian Optimisation and Optimal Transport

DeepArchitect: Automatically Designing and Training Deep Architectures

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

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