Hierarchical Walking Transformer for Object Re-Identification
Xudong Tian, Jun Liu, Zhizhong Zhang, Chengjie Wang, Yanyun Qu, Yuan Xie, Lizhuang Ma
2022年份
6被引次数
摘要
Recently, transformer purely based on attention mechanism has been applied to a wide range of tasks and achieved impressive performance. Though extensive efforts have been made, there are still drawbacks to the transformer architecture which hinder its further applications: (i) the quadratic complexity brought by attention mechanism; (ii) barely incorporated inductive bias.
问问这篇 Paper
问问你的智能体。
Lune 读过与它相关的顶会 Paper,每个回答都会注明依据哪几篇。
相关 Paper
- Chunk, Align, Select: A Simple Long-sequence Processing Method for TransformersJiawen Xie, Pengyu Cheng, Xiao Liang, Yong Dai 等ACL 2024
- Flowformer: Linearizing Transformers with Conservation FlowsHaixu Wu, Jialong Wu, Jiehui Xu, Jianmin Wang 等ICML 2022 · 被引用 130 次
- The Unstoppable Rise of Computational Linguistics in Deep LearningJames HendersonACL 2020 · 被引用 4 次
- Mega: Moving Average Equipped Gated AttentionXuezhe Ma, Chunting Zhou, Xiang Kong, Junxian He 等ICLR 2023 · 被引用 36 次
- T-former: An Efficient Transformer for Image InpaintingYe Deng, Siqi Hui, Sanping Zhou, Deyu Meng 等ACM MM 2022 · 被引用 58 次
