晓飞的算法工程笔记

论文: Training data-efficient image transformers & distillation through attention 论文地址：h...

论文: MViTv2: Improved Multiscale Vision Transformers for Classification and Detection 论...

论文: Multiscale Vision Transformers 论文地址：https://arxiv.org/abs/2104.11227 论文代码：https://...

论文: LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference 论文地址：https:...

论文: Going deeper with Image Transformers 论文地址：https://arxiv.org/abs/2103.17239 论文代码：ht...

论文: How Much More Data Do I Need? Estimating Requirements for Downstream Tasks 论文地址：ht...

论文: CvT: Introducing Convolutions to Vision Transformers 论文地址：https://arxiv.org/abs/21...

论文: DeepViT: Towards Deeper Vision Transformer 论文地址：https://arxiv.org/abs/2103.11886 论...

论文: Should All Proposals be Treated Equally in Object Detection? 论文地址：https://arxiv.or...

论文: Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Rec...

论文: Swin Transformer: Hierarchical Vision Transformer using Shifted Windows 论文地址：https...

论文: Incorporating Convolution Designs into Visual Transformers 论文地址：https://arxiv.org/...

论文: Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Conv...

论文: Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet 论文地址：ht...

论文: PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution 论文地址：h...

论文: FasterViT: Fast Vision Transformers with Hierarchical Attention 论文地址：https://arxiv...

论文: LORS: Low-rank Residual Structure for Parameter-Efficient Network Stacking 论文地址：ht...

论文: SURE: SUrvey REcipes for building reliable and robust deep networks 论文地址：https://a...

论文: Conditional Positional Encodings for Vision Transformers 论文地址：https://arxiv.org/ab...