09 2023 档案

【NIPS2021】Focal Self-attention for Local-Global Interactions in Vision Transformers
摘要：来自微软（*^____^*） 论文地址：[2107.00641] Focal Self-attention for Local-Global Interactions in Vision Transformers (arxiv.org) 代码地址：microsoft/Focal-Transforme 阅读全文
posted @ 2023-09-18 20:34 ninisong 阅读(84) 评论(1) 推荐(1) 编辑
【CVPR2022】Shunted Self-Attention via Multi-Scale Token Aggregation
摘要：来自CVPR2022 基于多尺度令牌聚合的分流自注意力 论文地址：[2111.15193] Shunted Self-Attention via Multi-Scale Token Aggregation (arxiv.org) 项目地址：https://github.com/OliverRensu 阅读全文
posted @ 2023-09-14 22:41 ninisong 阅读(236) 评论(0) 推荐(0) 编辑
【论文阅读】CAT: Cross Attention in Vision Transformer
摘要：来自快手(ฅ′ω`ฅ) 论文地址：[2106.05786] CAT: Cross Attention in Vision Transformer (arxiv.org) 项目地址：https://github.com/linhezheng19/CAT 一、Abstract 由于Transformer 阅读全文
posted @ 2023-09-07 11:07 ninisong 阅读(1641) 评论(1) 推荐(1) 编辑
【ICML2022】Understanding The Robustness in Vision Transformers
摘要：来自NUS&NVIDIA 文章地址：[2204.12451] Understanding The Robustness in Vision Transformers (arxiv.org) 项目地址：https://github.com/NVlabs/FAN 一、Motivation CNN使用滑动 阅读全文
posted @ 2023-09-06 10:51 ninisong 阅读(66) 评论(1) 推荐(1) 编辑