Supplementary Material: Ranking Neural Checkpoints

In this section, we describe the datasets used for the downstream tasks as shown in Table 1. More specifically, Caltech101 [2] contains 101 classes, including animals, airplanes, chairs and etc, the image size varies from 200 to 300 pixels per edge. Flowers102 [6] have 102 classes, with 40 to 248 training images per class, each image has at least 500 pixels. Patch Camelyon [10] contains 327,680 images of histopathologic scans of lymph node sections with image size of 96x96, which is collected to predict the presence of metastatic tissue. Sun397 [11] is a scenery benchmark with 397 classes, including cathedral, staircase, shelter, river, or archipelago. There are at least 100 images per class. The images are in 200x200 or higher resolutions. We believe the dataset portfolio well represents a broad set of vision tasks.