A class-based styling approach for Real-Time Domain Adaptation in Semantic Segmentation applied within the realm of autonomous driving solutions. Final project from MLDL course 2020/2021
-
Updated
Sep 1, 2022 - Python
A class-based styling approach for Real-Time Domain Adaptation in Semantic Segmentation applied within the realm of autonomous driving solutions. Final project from MLDL course 2020/2021
The official GitHub page for paper"Stochastic Adversarial Networks for Multi-Domain Text Classification"
(WIP) A simple program designed to optimize an enemy AI in Connect-4 using adversarial reinforcement learning
Adversarial Feature Hallucination in a Supervised Contrastive Space for Few-Shot Learning of Provenance in Paintings
Studied the impact of adversarial attacks on RNN Based load forecasting model.
The source code of our BIBM 2019 paper "Molecular Graph Generation with Deep Reinforced Multitask Network and Adversarial Imitation Learning".
Deep Adversarially-Enhanced k-Nearest Neighbors
PyTorch Implementation of IEEE/ACM CHASE 2021 paper "STranGAN: Adversarially-Learnt Spatial Transformer for Scalable Human Activity Recognition"
Independent Causal Mechanisms on 3D point clouds
Several Projects about AI in Python.
Introducing backdoors in neural networks through parameter-level manipulation.
[Partial] RADLER: (adversarially) Robust Adversarial Distributional LEaRner
Learning-guided Graph Dual Adversarial Domain Alignment (LG-DADA) framework for predicting a target graph from a source graph.
Fairness, Accountability, Confidentiality, Transparency in AI (FACT-AI).
Undirected graphical models are compact representations of joint probability distributions over random variables. To solve inference tasks of interest, graphical models of arbitrary topology can be trained using empirical risk minimization. However, to solve inference tasks that were not seen during training, these models (EGMs) often need to be…
DeepXplore (https://arxiv.org/abs/1705.06640) is a white-box framework for testing deep neural networks. Here, I have used the examples generated by the framework to retrain LeNet-5, LeNet-4 and LeNet-1.
ECE C147: Neural Networks & Deep Learning. Repository for "Developing Robust Networks to Defend Against Adversarial Examples". Implementing adversarial data augmentation on CNNs and RNNs.
This repository contains the implementation of a Part-of-Speech (POS) tagging system using Hidden Markov Models (HMMs) along with various decoding techniques and adversarial training strategies for sequence labeling tasks. Project for course DSCI 599 - Optimization Techniques for Data Science, Fall 2023
Unsupervised Machine Translation Model for data augmentation
Official repository for ICLR'24 paper "Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training"
Add a description, image, and links to the adversarial-learning topic page so that developers can more easily learn about it.
To associate your repository with the adversarial-learning topic, visit your repo's landing page and select "manage topics."