Dec 6, 2021
Speaker · 0 followers
Speaker · 103 followers
When faced with distribution shift at test time, deep neural networks often make inaccurate predictions with unreliable uncertainty estimates. While improving the robustness of neural networks is one promising approach to mitigate this issue, an appealing alternative to robustifying networks against all possible test-time shifts is to instead adapt them to unlabeled test data. In this paper, we propose a Bayesian model relating unlabeled data from the shifted test inputs to the classifier parameters being inferred and show how we can instantiate approximate inference in this model with a simple test-time adaptation procedure. We evaluate our method on a variety of distribution shifts for image classification, including image corruptions, natural distribution shifts, and domain adaptation settings, and show that our method improves both accuracy and uncertainty estimation.When faced with distribution shift at test time, deep neural networks often make inaccurate predictions with unreliable uncertainty estimates. While improving the robustness of neural networks is one promising approach to mitigate this issue, an appealing alternative to robustifying networks against all possible test-time shifts is to instead adapt them to unlabeled test data. In this paper, we propose a Bayesian model relating unlabeled data from the shifted test inputs to the classifier parame…
Account · 1.9k followers
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Professional recording and live streaming, delivered globally.
Presentations on similar topic, category or speaker
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Grisha Szep, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Ruihan Wu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Amir Hertz, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Zaixi Zhang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
MH Tessler, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%