Jun Station 준스테이션

https://arxiv.org/abs/2110.02178 MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer Light-weight convolutional neural networks (CNNs) are the de-facto for mobile vision tasks. Their spatial inductive biases allow them to learn representations with fewer parameters across different vision tasks. However, these networks are spatially local. arxiv.org 사실 2022년도에 나온 건 v..

[참고 사이트] https://deep-learning-study.tistory.com/728 [논문 읽기] Swin Transforemr(2021), Hierarchical Vision Transformer using Shifted Windows 안녕하세요, 오늘 읽은 논문은 Swin Transformer: Hierarchical VIsion Transformer using Shifted Windows 입니다. Swin Transformer는 transformer 구조를 object detection에 적용한 모델입니다. text에 비.. deep-learning-study.tistory.com 이를 응용한 UNet 형태의 네트워크 [논문] https://arxiv.org/pdf/2105.05537v1..

[참고 사이트] https://kmhana.tistory.com/27 Have A Nice AI kmhana.tistory.com [원 논문] https://arxiv.org/pdf/2010.11929.pdf [ViT 흐름에 대한 정리글] https://nuguziii.github.io/survey/S-007/ Vision Transformer Vision Transformer 흐름에 대해 정리한 글입니다. nuguziii.github.io [깃허브] https://github.com/The-AI-Summer/self-attention-cv GitHub - The-AI-Summer/self-attention-cv: Implementation of various self-attention mechanism..