Skip to main content
. Author manuscript; available in PMC: 2023 Jun 6.
Published in final edited form as: Comput Vis ECCV. 2021 Jan 10;12535:355–364. doi: 10.1007/978-3-030-66415-2_23

Table 1.

The different pre-trained CNN model as feature extractors and the output feature sizes

CNN model Output feature size
AlexNet [12] 256 × 5 × 5
VggNet11 [17] 512 × 6 × 6
ResNet18 [8] 512 × 7 × 7
MobileNet_v2 [15] 1280 × 4 × 4