Channel and spatial attention based deep object co-segmentation
Channel and spatial attention based deep object co-segmentation
复制标题
DOI：
10.1016/j.knosys.2020.106550
复制
发表时间：
2021-01-09
影响因子：
8.8
通讯作者：
Hilton, Adrian
中科院分区：
文献类型：
--
作者：
Chen, Jia;Chen, Yasong;Hilton, Adrian
目标联合分割是一项具有挑战性的任务，其目标是同时分割多幅图像中的共同目标。通常，需要找到同一对象的公共信息来解决这个问题。对于各种场景，不同图像中的共同对象仅具有相同的语义信息。本文提出了一种基于通道和空间注意力的深度对象联合分割方法，将注意力机制与深度神经网络相结合，以增强共同的语义信息。本课题采用的是连体编解码结构。首先，编码器网络被用来提取图像对的低层和高层特征。其次，在通道域和空间域引入了改进的注意机制，增强了常见对象的多层次语义特征。然后，解码器模块接受增强的特征图并生成两个图像的掩模。最后，我们评估我们的方法在常用的数据集上的共同分割任务。实验结果表明，该方法具有较好的性能。(C)2020 Elsevier B.V.保留所有权利。
Object co-segmentation is a challenging task, which aims to segment common objects in multiple images at the same time. Generally, common information of the same object needs to be found to solve this problem. For various scenarios, common objects in different images only have the same semantic information. In this paper, we propose a deep object co-segmentation method based on channel and spatial attention, which combines the attention mechanism with a deep neural network to enhance the common semantic information. Siamese encoder and decoder structure are used for this task. Firstly, the encoder network is employed to extract low-level and high-level features of image pairs. Secondly, we introduce an improved attention mechanism in the channel and spatial domain to enhance the multi-level semantic features of common objects. Then, the decoder module accepts the enhanced feature maps and generates the masks of both images. Finally, we evaluate our approach on the commonly used datasets for the co-segmentation task. And the experimental results show that our approach achieves competitive performance. (C) 2020 Elsevier B.V. All rights reserved.