Training-Free Transformer Architecture Search With Zero-Cost Proxy Guided Evolution

Transformers have shown remarkable performance, however, their architecture design is a time-consuming process that demands expertise and trial-and-error. Thus, it is worthwhile to investigate efficient methods for automatically searching high-performance Transformers via Transformer Architecture Se...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 46(2024), 10 vom: 28. Sept., Seite 6525-6541
1. Verfasser: Zhou, Qinqin (VerfasserIn)
Weitere Verfasser: Sheng, Kekai, Zheng, Xiawu, Li, Ke, Tian, Yonghong, Chen, Jie, Ji, Rongrong
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2024
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article