Oct. 21, 2022, 1:16 a.m. | Stefan Kolek, Duc Anh Nguyen, Ron Levie, Joan Bruna, Gitta Kutyniok

cs.CV updates on arXiv.org arxiv.org

We present CartoonX (Cartoon Explanation), a novel model-agnostic explanation
method tailored towards image classifiers and based on the rate-distortion
explanation (RDE) framework. Natural images are roughly piece-wise smooth
signals -- also called cartoon-like images -- and tend to be sparse in the
wavelet domain. CartoonX is the first explanation method to exploit this by
requiring its explanations to be sparse in the wavelet domain, thus extracting
the relevant piece-wise smooth part of an image instead of relevant
pixel-sparse regions. We …

arxiv cartoon classifiers image

Senior Machine Learning Engineer

@ GPTZero | Toronto, Canada

ML/AI Engineer / NLP Expert - Custom LLM Development (x/f/m)

@ HelloBetter | Remote

Doctoral Researcher (m/f/div) in Automated Processing of Bioimages

@ Leibniz Institute for Natural Product Research and Infection Biology (Leibniz-HKI) | Jena

Seeking Developers and Engineers for AI T-Shirt Generator Project

@ Chevon Hicks | Remote

Director, Venture Capital - Artificial Intelligence

@ Condé Nast | San Jose, CA

Senior Molecular Imaging Expert (Senior Principal Scientist)

@ University of Sydney | Cambridge (USA)