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

The performance of computer vision models are susceptible to unexpectedchanges in input images, known as common corruptions (e.g. noise, blur,illumination changes, etc.), that can hinder their reliability when deployed inreal scenarios. These corruptions are not always considered to test modelgeneralization and robustness. In this survey, we present a comprehensiveoverview of methods that improve the robustness of computer vision modelsagainst common corruptions. We categorize methods into four groups based on themodel part and training method addressed: data augmentation, representationlearning, knowledge distillation, and network components. We also coverindirect methods for generalization and mitigation of shortcut learning,potentially useful for corruption robustness. We release a unified benchmarkframework to compare robustness performance on several datasets, and addressthe inconsistencies of evaluation in the literature. We provide an experimentaloverview of the base corruption robustness of popular vision backbones, andshow that corruption robustness does not necessarily scale with model size. Thevery large models (above 100M parameters) gain negligible robustness,considering the increased computational requirements. To achieve generalizableand robust computer vision models, we foresee the need of developing newlearning strategies to efficiently exploit limited data and mitigate unwantedor unreliable learning behaviors.

Larger is not Better: A Survey on the Robustness of Computer Vision Models against Common Corruptions