Uncertainty Surrogates for Deep Learning
This addresses the need for reliable uncertainty estimation and out-of-distribution detection in deep learning, with potential applications in safety-critical domains, though it appears incremental as it builds on existing feature-based methods.
The paper tackles the problem of estimating prediction uncertainty in deep networks by introducing uncertainty surrogates, which are features forced to match predefined patterns, and shows that this approach is superior to state-of-the-art methods on standard metrics while also improving computational efficiency and robustness.
In this paper we introduce a novel way of estimating prediction uncertainty in deep networks through the use of uncertainty surrogates. These surrogates are features of the penultimate layer of a deep network that are forced to match predefined patterns. The patterns themselves can be, among other possibilities, a known visual symbol. We show how our approach can be used for estimating uncertainty in prediction and out-of-distribution detection. Additionally, the surrogates allow for interpretability of the ability of the deep network to learn and at the same time lend robustness against adversarial attacks. Despite its simplicity, our approach is superior to the state-of-the-art approaches on standard metrics as well as computational efficiency and ease of implementation. A wide range of experiments are performed on standard datasets to prove the efficacy of our approach.