paper-with-me

홈 › Papers

Unadversarial Examples: Designing Objects for Robust Vision

2020-12-22 · NeurIPS 2021 12 · Hadi Salman, Andrew Ilyas, Logan Engstrom, Sai Vemprala, Aleksander Madry, Ashish Kapoor

We study a class of realistic computer vision settings wherein one can influence the design of the objects being recognized. We develop a framework that leverages this capability to significantly improve vision models' performance and robustness. This framework exploits the sensitivity of modern machine learning algorithms to input perturbations in order to design "robust objects," i.e., objects that are explicitly optimized to be confidently detected or classified. We demonstrate the efficacy of the framework on a wide variety of vision-based tasks ranging from standard benchmarks, to (in-simulation) robotics, to real-world experiments. Our code can be found at https://git.io/unadversarial .

📄 PDF Abstract BibTeX arXiv:2012.12235

Code (2)

lengstrom/gitlinks
microsoft/unadversarial pytorch

Tasks

BIG-bench Machine LearningSensitivity

Similar Papers 제목 키워드 기반

NSA: Naturalistic Support Artifact to Boost Network Confidence

2023-07-27 · Abhijith Sharma, Phil Munz, Apurva Narayan

Visual AI systems are vulnerable to natural and synthetic physical corruption in the real-world. Such corruption often arises unexpectedly and alters the model's performance. In recent years, the primary focus has been o…

Stopping GAN Violence: Generative Unadversarial Networks

2017-03-07 · Samuel Albanie, Sébastien Ehrhardt, João F. Henriques

While the costs of human violence have attracted a great deal of attention from the research community, the effects of the network-on-network (NoN) violence popularised by Generative Adversarial Networks have yet to be a…

Developing and Defeating Adversarial Examples

2020-08-23 · Ian McDiarmid-Sterling, Allan Moser

Breakthroughs in machine learning have resulted in state-of-the-art deep neural networks (DNNs) performing classification tasks in safety-critical applications. Recent research has demonstrated that DNNs can be attacked …

BIG-bench Machine Learning

Depth from Camera Motion and Object Detection

2021-03-02 · CVPR 2021 1 · Brent A. Griffin, Jason J. Corso

This paper addresses the problem of learning to estimate the depth of detected objects given some measurement of camera motion (e.g., from robot kinematics or vehicle odometry). We achieve this by 1) designing a recurren…

Objectobject-detectionObject Detection

Symmetric Monoidal Categories with Attributes

2021-01-26 · Spencer Breiner, John S. Nolan

When designing plans in engineering, it is often necessary to consider attributes associated to objects, e.g. the location of a robot. Our aim in this paper is to incorporate attributes into existing categorical formalis…

Attribute