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

Neural network classifiers can largely rely on simple spurious features, suchas backgrounds, to make predictions. However, even in these cases, we show thatthey still often learn core features associated with the desired attributes ofthe data, contrary to recent findings. Inspired by this insight, we demonstratethat simple last layer retraining can match or outperform state-of-the-artapproaches on spurious correlation benchmarks, but with profoundly lowercomplexity and computational expenses. Moreover, we show that last layerretraining on large ImageNet-trained models can also significantly reducereliance on background and texture information, improving robustness tocovariate shift, after only minutes of training on a single GPU.

Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations