Performance Analysis
Table 1 Additional experiments in terms of classification Accuracy
We thank the reviewers for their valuable comments. We will add suggested experiments, references, and fix typos in the updated version. Take the large-scale ImageNet as an example. A3: Please refer to Table 1a and A2@R#1 for additional results on ImageNet. We see that the weights on the diagonal are higher.
No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems
We then use these approximate subclass labels as a form of noisy supervision in a distributionally robust optimization objective.
Target alignment in truncated kernel ridge regression
We show that TKRR can achieve a fast rate of convergence in the over-aligned regime.
Appendix: Boosting Out-of-distribution Detection with Typical Features A Type I error and type II error in OOD detection
In the literature on OOD detection, the type II error is also denoted by "FPR
