CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

A game theoretic approach to explain the output of any machine learning model.

YSDA course in Natural Language Processing

My continuously updated Machine Learning, Probabilistic Models and Deep Learning notes and demos (2000+ slides) 我不间断更新的机器学习，概率模型和深度学习的讲义(2000+页)和视频链接

An adversarial example library for constructing attacks, building defenses, and benchmarking both

DeepFashion2 Dataset https://arxiv.org/pdf/1901.07973.pdf

Handout for the tutorial "Creating publication-quality figures with matplotlib"

Training PyTorch models with differential privacy

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

Pytorch implementation of set transformer

Tutorial notebooks for hls4ml

PyTorch Implementation of "Large-Scale Image Retrieval with Attentive Deep Local Features"

A Tensorflow implementation of a Variational Autoencoder for the deep learning course at the University of Southern California (USC).

Notebooks for reproducing the paper "Computer Vision with a Single (Robust) Classifier"

Provably defending pretrained classifiers including the Azure, Google, AWS, and Clarifai APIs

Starter kit for the CVPR 2020 RANSAC tutorial benchmark

[BRH YT CHANNEL] This repo contains all the code and ressources you need for the Zynq tutorials, ready to copy and paste.

PyTorch code for No-Reference Image Quality Assessment on KonIQ-10k

Code for our S&P'21 paper: Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding

All the code for a series of Medium articles on Approximate Nearest Neighbors

Implementation of method described in http://openaccess.thecvf.com/content_ICCV_2019/papers/Le_Cacheux_Modeling_Inter_and_Intra-Class_Relations_in_the_Triplet_Loss_for_ICCV_2019_paper.pdf

A PyTorch implementation for the Recsys 2020 paper: Revisiting Adversarially Learned Injection Attacks Against Recommender Systems

PyTorch Implementation of NeurIPS 2020 paper "Learning Sparse Prototypes for Text Generation"

Code for the paper "Autoregressive Perturbations for Data Poisoning" (NeurIPS 2022)

code for MS thesis "White-Box Adversarial Attacks on classification in NLP"

cifar10 using Bag-of-features method (no NN, only 80% accuracy)