In the realm of deep learning, spatial attention mechanisms have emerged as a vital method for enhancing the performance of convolutional neural networks. However, these mechanisms possess inherent limitations that cannot be overlooked. This work delves into the mechanism of spatial attention and reveals a new insight. It is that the mechanism essentially addresses the issue of convolutional parameter sharing. By addressing this issue, the convolutional kernel can efficiently extract features by employing varying weights at distinct locations. However, current spatial attention mechanisms focus on reweighting spatial features through attention, which is insufficient to address the fundamental challenge of parameter sharing in convolutions involving larger kernels. In response to this challenge, we introduce a novel attention mechanism known as Receptive-Field Attention (RFA). Compared to existing spatial attention methods, RFA not only concentrates on the receptive-field spatial features but also offers effective attention weights for large convolutional kernels. Building upon the RFA concept, a Receptive-Field Attention Convolution (RFAConv) is proposed to supplant the conventional standard convolution. Notably, it offers nearly negligible increment of computational overhead and parameters, while significantly improving network performance. Furthermore, this work reveals that current spatial attention mechanisms require enhanced prioritization of receptive-field spatial features to optimize network performance. To validate the advantages of the proposed methods, we conduct many experiments across several authoritative datasets, including ImageNet, Places365, COCO, VOC, and Roboflow. The results demonstrate that the proposed methods bring about significant advancements in tasks, such as image classification, object detection, and semantic segmentation, surpassing convolutional operations constructed using current spatial attention mechanisms. Presently, the code and pre-trained models for the associated tasks have been made publicly available at https://github.com/Liuchen1997/RFAConv.
扫码关注我们
求助内容:
应助结果提醒方式:
