Robust Computer Vision beyond Lₚ Adversaries
Deep learning computer vision systems, integral to technologies such as self-driving cars, facial recognition, and content moderation, require robustness against diverse perturbations to ensure reliability and safety. Examples of such perturbations include variations in lighting conditions, occlusio...
Main Author: | Leclerc, Guillaume |
---|---|
Other Authors: | Madry, Aleksander |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2024
|
Online Access: | https://hdl.handle.net/1721.1/156330 https://orcid.org/0009-0000-2681-9848 |
Similar Items
-
Adversarial attacks and adversarial robustness in computational pathology
by: Narmin Ghaffari Laleh, et al.
Published: (2022-09-01) -
Generative adversarial networks in computer vision: image synthesis and manipulation
by: Dong Lingfeng, et al.
Published: (2024-01-01) -
A Review of Generative Adversarial Networks for Computer Vision Tasks
by: Ana-Maria Simion, et al.
Published: (2024-02-01) -
Feature-driven new sound category formation: computational implementation with the L2LP model and beyond
by: Kakeru Yazawa, et al.
Published: (2023-12-01) -
Review on Generative Adversarial Networks: Focusing on Computer Vision and Its Applications
by: Sung-Wook Park, et al.
Published: (2021-05-01)