Dai Shi

Independent researcher, the sole author of TransNeXt.

[Dai Shi @DaiShiResearch]

I think this is an excellent introduction to TransNeXt. Highly recommended!

[NABLAS株式会社 @nablas_inc]

社内勉強会の資料「TransNeXt: Robust Foveal Visual Perception for Vision Transformers」を公開！

人間の視覚に似た視覚的モデリング手法である大域性と局所性を併せ持つ注意機構を導入したビジョントランスフォーマーアーキテクチャTransNeXtについて紹介しています。
https://t.co/l3I9DDH1g3

[Dai Shi @DaiShiResearch]

@nablas_inc これはTransNeXtに関する非常に素晴らしい紹介資料だと思います。丁寧に作ってくださった方々に感謝いたします。

[Dai Shi @DaiShiResearch]

@wjscheirer Pleased to see that all three results match my voting choices. 🤗

[Dai Shi @DaiShiResearch]

Excited to present our #TransNeXt poster at #CVPR! 🖼️ We'll be showcasing it from 17:15 to 18:45 at Poster Session 4 in Exhibit Hall (Arch 4A-E), Poster #307. Stop by to read our poster, and feel free to email me if you want to discuss more! #CVPR2024 #ComputerVision #AI #ML

[Dai Shi @DaiShiResearch]

Explore our new state-of-the-art visual backbone, #TransNeXt, which has been accepted by #CVPR2024. We have released all code, model weights, and training logs! Check it out here:

Paper: https://t.co/1G1Dk0B0Gd

Code: https://t.co/OPfmcS2ov3

Models: https://t.co/q6KiIWVqsf