[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"
Thanks for your great work! Does these contrastive learning methods' performance on ImageNet refer to finetuning results? If so, since those papers only report linear evaluation results, where did you get the finetuning score?
Thanks for your great work! Does these contrastive learning methods' performance on ImageNet refer to finetuning results? If so, since those papers only report linear evaluation results, where did you get the finetuning score?