Impact of realistic properties of the point spread function on classification tasks to reveal a possible distribution shift
Dec 2, 2022
Speakers
Patrick Müller
Speaker · 0 followers
Alexander Braun
Speaker · 0 followers
Margret Keuper
Speaker · 0 followers
About
Image classification is a long-standing task in computer vision with deep neuralnetworks (DNN) producing excellent results on various challenges. However, theyare required not only to perform highly accurate on benchmarks such as ImageNet,but also to robustly handle images in adverse conditions, such as modified lighting, sharpness, weather conditions and image compression. Various benchmarksaimed to measure robustness show that neural networks perform differently wellunder distribution shifts. While datasets such as ImageNet-C model for example common corruptions such as blur and adverse weather conditions, we argue thatthe properties of the optical system and the potentially resulting complex lens blurare insufficiently well studied in the literature. This study evaluates the impact ofrealistic optical corruptions on the ImageNet classification. The proposed complexcorruption kernels are direction and wavelength dependent and include chromaticaberration, which are all to be expected in realistic scenarios such as autonomousdriving applications. Our experiments on twelve different DNN models show significant differences of more than 5Image classification is a long-standing task in computer vision with deep neuralnetworks (DNN) producing excellent results on various challenges. However, theyare required not only to perform highly accurate on benchmarks such as ImageNet,but also to robustly handle images in adverse conditions, such as modified lighting, sharpness, weather conditions and image compression. Various benchmarksaimed to measure robustness show that neural networks perform differently wellunder distribution shifts.…
Organizer
NeurIPS 2022
Account · 954 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Continual Learning In Environments With Polynomial Mixing Times
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
A gradient sampling method with complexity guarantees for Lipschitz functions in low and high dimensions
Watch later
Damek Davis, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Volume-based Performance not Guaranteed by Promising Patch-based Results in Medical Imaging
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning in Congestion Games with Bandit Feedback
Watch later
Zhihan Xiong, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Signal Recovery with Non-Expansive Generative Network Priors
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Collaborating with language models for embodied reasoning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%