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

In this paper, our goal is to adapt a pre-trained convolutional neuralnetwork to domain shifts at test time. We do so continually with the incomingstream of test batches, without labels. The existing literature mostly operateson artificial shifts obtained via adversarial perturbations of a test image.Motivated by this, we evaluate the state of the art on two realistic andchallenging sources of domain shifts, namely contextual and semantic shifts.Contextual shifts correspond to the environment types, for example, a modelpre-trained on indoor context has to adapt to the outdoor context on CORe-50.Semantic shifts correspond to the capture types, for example a modelpre-trained on natural images has to adapt to cliparts, sketches, and paintingson DomainNet. We include in our analysis recent techniques such asPrediction-Time Batch Normalization (BN), Test Entropy Minimization (TENT) andContinual Test-Time Adaptation (CoTTA). Our findings are three-fold: i)Test-time adaptation methods perform better and forget less on contextualshifts compared to semantic shifts, ii) TENT outperforms other methods onshort-term adaptation, whereas CoTTA outpeforms other methods on long-termadaptation, iii) BN is most reliable and robust. Our code is available athttps://github.com/tommiekerssies/Evaluating-Continual-Test-Time-Adaptation-for-Contextual-and-Semantic-Domain-Shifts.

Evaluating Continual Test-Time Adaptation for Contextual and Semantic Domain Shifts