why there is no intermediate fine-tuning for one-class ImageNet-30?

[wangherr]

In my view, there is no difference between one-class ImageNet-30 and one-class cifar10.

why intermediate fine-tuning is ok for one-class cifar10, but is not ok for one-class ImageNet-30?

[JulietLJY]

Hi! The reason is that there is an overlap between ImageNet-30 and ImageNet-1k. Consequently, if we conduct fine-tuning on ImageNet-30, it would transform into a straightforward binary-classification task rather than an out-of-distribution (OOD) detection task.