Sequential Adversarial

Sequential adversarial methods leverage the power of adversarial training across multiple steps or time points, improving model robustness and performance in various applications. Current research focuses on applying this framework to diverse problems, including robot control, forecasting, and medical image synthesis, often employing generative adversarial networks (GANs) or other sequential models. This approach enhances the ability to learn complex temporal dependencies and improve the generalization capabilities of models, leading to more reliable and effective systems in fields ranging from robotics to healthcare.

Papers

May 21, 2024

Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllers
Fan Shi, Chong Zhang, Takahiro Miki, Joonho Lee, Marco Hutter, Stelian Coros
Adversarial Attack Deep Reinforcement Learning Legged Locomotion Robustness Evaluation Quadrupedal Locomotion Adversarial Pattern Sequential Adversarial

February 13, 2024

Forecasting for Swap Regret for All Downstream Agents
Aaron Roth, Mirah Shi
State of the Art Forecasting Downstream Task Dynamic Regret Linear Dependence Swap Regret Sequential Adversarial

September 8, 2023

Robot Localization and Mapping Final Report -- Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry
Akankshya Kar, Sajal Maheshwari, Shamit Lal, Vinay Sameer Raja Kad
Generative Adversarial Network Pose Estimation Depth Estimation Visual Odometry Robot Localization Sequential Adversarial

August 27, 2023

Bi-Modality Medical Image Synthesis Using Semi-Supervised Sequential Generative Adversarial Networks
Xin Yang, Yi Lin, Zhiwei Wang, Xin Li, Kwang-Ting Cheng
Medical Image Synthesis Multi Modality Image Sequential Adversarial

December 16, 2022

Improving self-supervised representation learning via sequential adversarial masking
Dylan Sam, Min Bai, Tristan McKinney, Li Erran Li
Self Supervised Representation Learning Learned Representation Masking Strategy Pretext Task Adversarial Mask Adaptive Mask Sequential Adversarial

Sequential Adversarial

Papers

Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllers

Forecasting for Swap Regret for All Downstream Agents

Robot Localization and Mapping Final Report -- Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry

Bi-Modality Medical Image Synthesis Using Semi-Supervised Sequential Generative Adversarial Networks

Improving self-supervised representation learning via sequential adversarial masking