27 citations · 30 across the 19 of their papers we have counts for
7 papers · 1 filter
Private and Stable Test-Time Adaptation with Differential Privacy
Zefeng Li, Qiaoyue Tang, Mathias Lecuyer +1
Test-time adaptation (TTA) can reduce error on new and different data by updating the model on these inputs during inference. However, these updates raise the issue of privacy w.r.…
A Closer Look at In-Distribution vs. Out-of-Distribution Accuracy for Open-Set Test-time Adaptation
Zefeng Li, Evan Shelhamer
Open-set test-time adaptation (TTA) updates models on new data in the presence of input shifts and unknown output classes. While recent methods have made progress on improving in-d…
ProtoTTA: Prototype-Guided Test-Time Adaptation
Mohammad Mahdi Abootorabi, Parvin Mousavi, Purang Abolmaesumi +1
Deep networks that rely on prototypes-interpretable representations that can be related to the model input-have gained significant attention for balancing high accuracy with inhere…
Self-Soupervision: Cooking Model Soups without Labels
Anthony Fuller, James R. Green, Evan Shelhamer
Model soups are strange and strangely effective combinations of parameters. They take a model (the stock), fine-tune it into multiple models (the ingredients), and then mix their p…
GeoCrossBench: Cross-Band Generalization for Remote Sensing
Hakob Tamazyan, Ani Vanyan, Alvard Barseghyan +3
The data for remote sensing is constantly acquired, and new data comes from a growing number and diversity of satellites, while the vast majority of labeled data comes from older s…
Asymmetric Duos: Sidekicks Improve Uncertainty
Tim G. Zhou, Evan Shelhamer, Geoff Pleiss
The go-to strategy to apply deep networks in settings where uncertainty informs decisions--ensembling multiple training runs with random initializations--is ill-suited for the extr…
Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
Saiyue Lyu, Shadab Shaikh, Frederick Shpilevskiy +2
We propose Adaptive Randomized Smoothing (ARS) to certify the predictions of our test-time adaptive models against adversarial examples. ARS extends the analysis of randomized smoo…