Guardado en:
Detalles Bibliográficos
Autores principales: Zhu, Guangyang, Zhang, Jianfeng, Feng, Yuanzhi, Lan, Hai
Formato: Preprint
Publicado: 2022
Materias:
Acceso en línea:https://arxiv.org/abs/2201.01410
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917788786884608
author Zhu, Guangyang
Zhang, Jianfeng
Feng, Yuanzhi
Lan, Hai
author_facet Zhu, Guangyang
Zhang, Jianfeng
Feng, Yuanzhi
Lan, Hai
contents Self-attention module shows outstanding competence in capturing long-range relationships while enhancing performance on vision tasks, such as image classification and image captioning. However, the self-attention module highly relies on the dot product multiplication and dimension alignment among query-key-value features, which cause two problems: (1) The dot product multiplication results in exhaustive and redundant computation. (2) Due to the visual feature map often appearing as a multi-dimensional tensor, reshaping the scale of the tensor feature to adapt to the dimension alignment might destroy the internal structure of the tensor feature map. To address these problems, this paper proposes a self-attention plug-in module with its variants, namely, Synthesizing Tensor Transformations (STT), for directly processing image tensor features. Without computing the dot-product multiplication among query-key-value, the basic STT is composed of the tensor transformation to learn the synthetic attention weight from visual information. The effectiveness of STT series is validated on the image classification and image caption. Experiments show that the proposed STT achieves competitive performance while keeping robustness compared to self-attention in the aforementioned vision tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2201_01410
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Synthesizer Based Efficient Self-Attention for Vision Tasks
Zhu, Guangyang
Zhang, Jianfeng
Feng, Yuanzhi
Lan, Hai
Computer Vision and Pattern Recognition
Machine Learning
Self-attention module shows outstanding competence in capturing long-range relationships while enhancing performance on vision tasks, such as image classification and image captioning. However, the self-attention module highly relies on the dot product multiplication and dimension alignment among query-key-value features, which cause two problems: (1) The dot product multiplication results in exhaustive and redundant computation. (2) Due to the visual feature map often appearing as a multi-dimensional tensor, reshaping the scale of the tensor feature to adapt to the dimension alignment might destroy the internal structure of the tensor feature map. To address these problems, this paper proposes a self-attention plug-in module with its variants, namely, Synthesizing Tensor Transformations (STT), for directly processing image tensor features. Without computing the dot-product multiplication among query-key-value, the basic STT is composed of the tensor transformation to learn the synthetic attention weight from visual information. The effectiveness of STT series is validated on the image classification and image caption. Experiments show that the proposed STT achieves competitive performance while keeping robustness compared to self-attention in the aforementioned vision tasks.
title Synthesizer Based Efficient Self-Attention for Vision Tasks
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2201.01410