no code implementations • 28 Sep 2022 • Chengjie Huang, Van Duong Nguyen, Vahdat Abdelzad, Christopher Gus Mannes, Luke Rowe, Benjamin Therien, Rick Salay, Krzysztof Czarnecki
Detecting OOD inputs is challenging and essential for the safe deployment of models.
no code implementations • 10 May 2022 • Rick Salay, Krzysztof Czarnecki
While research in addressing these limitations is active, in this paper, we argue that a fundamentally different approach is needed to address them.
no code implementations • 8 Feb 2022 • Boyue Caroline Hu, Lina Marsso, Krzysztof Czarnecki, Rick Salay, Huakun Shen, Marsha Chechik
In this paper, we address the need for defining machine-verifiable reliability requirements for MVCs against transformations that simulate the full range of realistic and safety-critical changes in the environment.
no code implementations • 30 Aug 2021 • Rick Salay, Krzysztof Czarnecki, Hiroshi Kuwajima, Hirotoshi Yasuoka, Toshihiro Nakae, Vahdat Abdelzad, Chengjie Huang, Maximilian Kahn, Van Duong Nguyen
In this paper, we propose the Integration Safety Case for Perception (ISCaP), a generic template for such a linking safety argument specifically tailored for perception components.
no code implementations • 25 Jun 2020 • Vahdat Abdelzad, Krzysztof Czarnecki, Rick Salay
In addition to comparing several OODD approaches using our proposed robustness score, we demonstrate that some optimization methods provide better solutions for OODD approaches.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • 7 Nov 2019 • Matt Angus, Krzysztof Czarnecki, Rick Salay
The detection of out of distribution samples for image classification has been widely researched.
2 code implementations • 23 Oct 2019 • Vahdat Abdelzad, Krzysztof Czarnecki, Rick Salay, Taylor Denounden, Sachin Vernekar, Buu Phan
Several approaches have been proposed to detect OOD inputs, but the detection task is still an ongoing challenge.
1 code implementation • 9 Oct 2019 • Sachin Vernekar, Ashish Gaurav, Vahdat Abdelzad, Taylor Denouden, Rick Salay, Krzysztof Czarnecki
By design, discriminatively trained neural network classifiers produce reliable predictions only for in-distribution samples.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
1 code implementation • 25 Sep 2019 • Sachin Vernekar, Ashish Gaurav, Vahdat Abdelzad, Taylor Denouden, Rick Salay, Krzysztof Czarnecki
In the context of OOD detection for image classification, one of the recent approaches proposes training a classifier called “confident-classifier” by minimizing the standard cross-entropy loss on in-distribution samples and minimizing the KLdivergence between the predictive distribution of OOD samples in the low-density“boundary” of in-distribution and the uniform distribution (maximizing the entropy of the outputs).
Out-of-Distribution Detection Out of Distribution (OOD) Detection
1 code implementation • 27 Apr 2019 • Sachin Vernekar, Ashish Gaurav, Taylor Denouden, Buu Phan, Vahdat Abdelzad, Rick Salay, Krzysztof Czarnecki
Discriminatively trained neural classifiers can be trusted, only when the input data comes from the training distribution (in-distribution).
no code implementations • 3 Mar 2019 • Krzysztof Czarnecki, Rick Salay
Perception is a safety-critical function of autonomous vehicles and machine learning (ML) plays a key role in its implementation.
no code implementations • 6 Dec 2018 • Taylor Denouden, Rick Salay, Krzysztof Czarnecki, Vahdat Abdelzad, Buu Phan, Sachin Vernekar
There is an increasingly apparent need for validating the classifications made by deep learning systems in safety-critical applications like autonomous vehicle systems.
no code implementations • 27 Nov 2018 • Buu Phan, Rick Salay, Krzysztof Czarnecki, Vahdat Abdelzad, Taylor Denouden, Sachin Vernekar
In many safety-critical applications such as autonomous driving and surgical robots, it is desirable to obtain prediction uncertainties from object detection modules to help support safe decision-making.
no code implementations • 5 Aug 2018 • Rick Salay, Krzysztof Czarnecki
In automotive development, safety is a critical objective, and the emergence of standards such as ISO 26262 has helped focus industry practices to address safety in a systematic and consistent way.
no code implementations • 7 Sep 2017 • Rick Salay, Rodrigo Queiroz, Krzysztof Czarnecki
We then provide a set of recommendations on how to adapt the standard to accommodate ML.