摘要：
本文是对于近年来一些多模态大模型工作的相关总结，重点是这些模型的演化路线，各自做了什么改进。 CLIP 论文链接：https://arxiv.org/abs/2103.00020 以往的图像模型都是采用有监督的预训练，需要在人工标注的数据集上进行学习，这限制了图像模型预训练的数据规模。 CLIP采用 阅读全文
摘要：
Self-Attention with Relative Position Representations * Authors: [[Peter Shaw]], [[Jakob Uszkoreit]], [[Ashish Vaswani]] 初读印象 comment:: (相对位置编码)提出了两个元 阅读全文
摘要：
Dual Attention Network for Scene Segmentation * Authors: [[Jun Fu]], [[Jing Liu]], [[Haijie Tian]], [[Yong Li]], [[Yongjun Bao]], [[Zhiwei Fang]], [[H 阅读全文
摘要：
Is Attention Better Than Matrix Decomposition? * Authors: [[Zhengyang Geng]], [[Meng-Hao Guo]], [[Hongxu Chen]], [[Xia Li]], [[Ke Wei]], [[Zhouchen Li 阅读全文
摘要：
SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation * Authors: [[Meng-Hao Guo]], [[Cheng-Ze Lu]], [[Qibin Hou]], [[Zhengning 阅读全文
摘要：
Deep Residual Learning for Image Recognition * Authors: [[Kaiming He]], [[Xiangyu Zhang]], [[Shaoqing Ren]], [[Jian Sun]] DOI: 10.1109/CVPR.2016.90 初读 阅读全文
摘要：
Relation Networks for Object Detection * Authors: [[Han Hu]], [[Jiayuan Gu]], [[Zheng Zhang]], [[Jifeng Dai]], [[Yichen Wei]] DOI: 10.1109/CVPR.2018.0 阅读全文
摘要：
Squeeze-and-Excitation Networks * Authors: [[Jie Hu]], [[Li Shen]], [[Samuel Albanie]], [[Gang Sun]], [[Enhua Wu]] Local library 初读印象 comment:: (SENet 阅读全文
摘要：
Local Relation Networks for Image Recognition * Authors: [[Han Hu]], [[Zheng Zhang]], [[Zhenda Xie]], [[Stephen Lin]] DOI: 10.1109/ICCV.2019.00356 @in 阅读全文
摘要：
CCNet: Criss-Cross Attention for Semantic Segmentation * Authors: [[Zilong Huang]], [[Xinggang Wang]], [[Yunchao Wei]], [[Lichao Huang]], [[Humphrey S 阅读全文