On-manifold Adversarial Data Augmentation Improves Uncertainty Calibration
| Autor: | Patel, Kanil, Beluch, William, Zhang, Dan, Pfeiffer, Michael, Yang, Bin |
|---|---|
| Rok vydání: | 2019 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | Uncertainty estimates help to identify ambiguous, novel, or anomalous inputs, but the reliable quantification of uncertainty has proven to be challenging for modern deep networks. In order to improve uncertainty estimation, we propose On-Manifold Adversarial Data Augmentation or OMADA, which specifically attempts to generate the most challenging examples by following an on-manifold adversarial attack path in the latent space of an autoencoder-based generative model that closely approximates decision boundaries between two or more classes. On a variety of datasets as well as on multiple diverse network architectures, OMADA consistently yields more accurate and better calibrated classifiers than baseline models, and outperforms competing approaches such as Mixup, as well as achieving similar performance to (at times better than) post-processing calibration methods such as temperature scaling. Variants of OMADA can employ different sampling schemes for ambiguous on-manifold examples based on the entropy of their estimated soft labels, which exhibit specific strengths for generalization, calibration of predicted uncertainty, or detection of out-of-distribution inputs. Comment: Accepted for oral at International Conference on Pattern Recognition, ICPR 2020. Nominated (top 4) for Best Industry Related Paper Award (BIRPA) |
| Databáze: | arXiv |
| Externí odkaz: |
|