Skip to yearly menu bar Skip to main content

Workshop: Workshop on Distribution Shifts: New Frontiers with Foundation Models

Channel Selection for Test-Time Adaptation Under Distribution Shift

Pedro Vianna · Muawiz Chaudhary · An Tang · Guy Cloutier · Guy Wolf · Michael Eickenberg · Eugene Belilovsky

Keywords: [ label distribution shift ] [ Test-time adaptation ] [ covariate shift ]


To ensure robustness and generalization to real-world scenarios, test-time adaptation has been recently studied as an approach to adjust models to a new data distribution during inference. Test-time batch normalization is a simple and popular method that achieved compelling performance on domain shift benchmarks by recalculating batch normalization statistics on test batches. However, in many practical applications this technique is vulnerable to label distribution shifts. We propose to tackle this challenge by only selectively adapting channels in a deep network, minimizing drastic adaptation that is sensitive to label shifts. We find that adapted models significantly improve the performance compared to the baseline models and counteract unknown label shifts.

Chat is not available.