Revisiting ResNets: Improved Training and Scaling Strategies Revisiting ...
MobileNERT: a Compact Task-Agnostic BERT for Resource-Limited Devices ht...
三爷爷是地地道道的农民,从未外出打工,也很少进城,一辈子都在跟黄土地打交道讨吃食。这两年,土地都被征收种了油菜花,家里的日子也逐渐变好,三爷爷...
RepVGG:Making VGG-style ConvNets Great Again https://arxiv.org/abs/2101....
Do We Really Need Explicit Position Encodings for Vision Transformers? h...
Training data-efficient image transformersa& distillation through attent...
AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCA...
CHARACTERIZING SIGNAL PROPAGATION TO CLOSE THE PERFORMANCE GAP IN UNNORM...
Learning Filter Pruning Criteria for Deep Convolutional Neural Networks ...