SparK
Public[ICLR'23 Spotlight?] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"
bertcnnconvnetconvolutional-neural-networksdeep-learningiclriclr2023instance-segmentationmaemask-rcnn
Creat：2023-01-05T21:19:34
Update：2025-03-26T21:31:55
https://arxiv.org/abs/2301.03580
1.4K
Stars
0
Stars Increase