Balanced single-shot object detection using cross-context attention-guided network
Balanced single-shot object detection using cross-context attention-guided network
复制标题
DOI：
10.1016/j.patcog.2021.108258
复制
发表时间：
2021-08-29
影响因子：
8
通讯作者：
Fan, Weiguo
中科院分区：
文献类型：
--
作者：
Miao, Shuyu;Du, Shanshan;Fan, Weiguo
在实际应用场景中，目标检测通常会遇到两个技术挑战，即高精度和高速度。虽然最新的基于无锚点检测的检测框架已经取得了突出的性能，但由于其模型复杂和速度慢，无法在现实场景中广泛应用。本文受人类视觉系统跨背景注意机制的启发，提出了一种基于跨背景注意引导网络(CCAGNet)的轻量级高效单镜头检测框架，以平衡检测的准确性和速度。CCAGNet使用注意引导机制来突出对象-协同区域的交互作用，并通过结合跨语境注意机制(CCAM)、接受场注意机制(RFAM)和语义融合注意机制(SfAM)来抑制非对象协同区域。我们的主要工作包括建立一种新的注意机制，同时考虑通道、空间、交叉和相邻区域的上下文信息。在公共基准数据集上的大量实验证明了该方法的可行性和有效性。据我们所知，CCAGNet在PascalVOC和MSCOCO上都获得了最先进的性能，在单次发射探测器的精度和速度之间进行了出色的权衡。特别是，在MSCOCO上，小目标检测的平均精度(AP)指标显著提高了17.0%。(C)爱思唯尔有限公司出版的《2021年》。
In real-world application scenarios, object detection usually encounters two technical challenges, i.e., high accuracy and high speed. Although the latest detection frameworks based on anchor-free detection have achieved outstanding performance, they cannot be widely used in real-world scenarios due to their model complexity and slow speed. In this paper, inspired by cross-context attention mechanism of human visual systems, we propose a light but effective single-shot detection framework using Cross-context Attention-guided Network (CCAGNet) to balance the accuracy and speed. CCAGNet uses attention-guided mechanism to highlight the interaction of object-synergy regions, and suppresses non-object-synergy regions by combining Cross-context Attention Mechanism (CCAM), Receptive Field Attention Mechanism (RFAM), and Semantic Fusion Attention Mechanism (SFAM). The main contribution of our work includes establishing a novel attention mechanism that takes the context information of channel, spatial, cross and adjacent-regions into consideration simultaneously. Extensive experiments demonstrate the feasibility and effectiveness of our method on the public benchmark datasets. To the best of our knowledge, CCAGNet obtains the state-of-the-art performance on both PascalVOC and MSCOCO with the excellent trade-off between accuracy and speed among single-shot detectors. Especially, the Average Precision (AP) metric is significantly improved by 17.0% on small object detection on MSCOCO. (c) 2021 Published by Elsevier Ltd.