The CCP method finds the class-wise quantiles of non-conformity scores on calibration data.

We thank all reviewers for their valuable comments. Below, we first address the common concerns and then answer the detailed questions. It leads to smaller bias (see Fig. A), which also agrees with Thm. 2. First, introducing latent variables can improve the sample quality (w.r.t. Indeed, we update Tab. 2 and obtain Tab. As stated in L290, a similar protocol is adopted in MDSM [34].

The first design helps the model focus more on the global context of the image as each patch could attend to the whole image areas. It reduces the local texture bias ofCNN.