Skip to yearly menu bar Skip to main content


Poster

Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts

Ha Manh Bui · Anqi Liu

Hall C 4-9 #2514
[ ] [ Project Page ] [ Paper PDF ]
[ Slides [ Poster
Tue 23 Jul 4:30 a.m. PDT — 6 a.m. PDT

Abstract:

Sampling-based methods, e.g., Deep Ensembles and Bayesian Neural Nets have become promising approaches to improve the quality of uncertainty estimation and robust generalization. However, they suffer from a large model size and high latency at test time, which limits the scalability needed for low-resource devices and real-time applications. To resolve these computational issues, we propose Density-Softmax, a sampling-free deterministic framework via combining a density function built on a Lipschitz-constrained feature extractor with the softmax layer. Theoretically, we show that our model is the solution of minimax uncertainty risk and is distance-aware on feature space, thus reducing the over-confidence of the standard softmax under distribution shifts. Empirically, our method enjoys competitive results with state-of-the-art techniques in terms of uncertainty and robustness, while having a lower number of model parameters and a lower latency at test time.

Chat is not available.