English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep Neural Networks are often brittle on image classification tasks andknown to misclassify inputs. While these misclassifications may be inevitable,all failure modes cannot be considered equal. Certain misclassifications (eg.classifying the image of a dog to an airplane) can perplex humans and result inthe loss of human trust in the system. Even worse, these errors (eg. a personmisclassified as a primate) can have odious societal impacts. Thus, in thiswork, we aim to reduce inexplicable errors. To address this challenge, we firstdiscuss methods to obtain the class-level semantics that capture the human'sexpectation ($M^h$) regarding which classes are semantically close {\em vs.}ones that are far away. We show that for popular image benchmarks (likeCIFAR-10, CIFAR-100, ImageNet), class-level semantics can be readily obtainedby leveraging either human subject studies or publicly available human-curatedknowledge bases. Second, we propose the use of Weighted Loss Functions (WLFs)to penalize misclassifications by the weight of their inexplicability. Finally,we show that training (or fine-tuning) existing classifiers with the proposedmethods lead to Deep Neural Networks that have (1) comparable top-1 accuracy,(2) more explicable failure modes on both in-distribution andout-of-distribution (OOD) test data, and (3) incur significantly less cost inthe gathering of additional human labels compared to existing works.

Not all Failure Modes are Created Equal: Training Deep Neural Networks for Explicable (Mis)Classification