计算机科学
帕斯卡(单位)
直觉
人工智能
注意力网络
架空(工程)
相互依存
理论计算机科学
计算机工程
机器学习
分布式计算
程序设计语言
政治学
认识论
哲学
法学
作者
Diganta Misra,Trikay Nalamada,Ajay Uppili Arasanipalai,Qibin Hou
标识
DOI:10.1109/wacv48630.2021.00318
摘要
Benefiting from the capability of building interdependencies among channels or spatial locations, attention mechanisms have been extensively studied and broadly used in a variety of computer vision tasks recently. In this paper, we investigate light-weight but effective attention mechanisms and present triplet attention, a novel method for computing attention weights by capturing crossdimension interaction using a three-branch structure. For an input tensor, triplet attention builds inter-dimensional dependencies by the rotation operation followed by residual transformations and encodes inter-channel and spatial information with negligible computational overhead. Our method is simple as well as efficient and can be easily plugged into classic backbone networks as an add-on module. We demonstrate the effectiveness of our method on various challenging tasks including image classification on ImageNet-1k and object detection on MSCOCO and PASCAL VOC datasets. Furthermore, we provide extensive insight into the performance of triplet attention by visually inspecting the GradCAM and GradCAM++ results. The empirical evaluation of our method supports our intuition on the importance of capturing dependencies across dimensions when computing attention weights. Code for this paper can be publicly accessed at https://github.com/LandskapeAI/triplet-attention.
科研通智能强力驱动
Strongly Powered by AbleSci AI