Li Liming, Zhao Shuguang, Sun Rui, Chai Xiaodong, Zheng Shubin, Chen Xingjie, Lv Zhaomin
School of Information Science and Technology, Donghua University, Shanghai 201620, China.
School of Urban Railway Transportation, Shanghai University of Engineering Science, Shanghai 201620, China.
Comput Intell Neurosci. 2021 Mar 30;2021:8861446. doi: 10.1155/2021/8861446. eCollection 2021.
This article proposes an innovative RGBD saliency model, that is, attention-guided feature integration network, which can extract and fuse features and perform saliency inference. Specifically, the model first extracts multimodal and level deep features. Then, a series of attention modules are deployed to the multilevel RGB and depth features, yielding enhanced deep features. Next, the enhanced multimodal deep features are hierarchically fused. Lastly, the RGB and depth boundary features, that is, low-level spatial details, are added to the integrated feature to perform saliency inference. The key points of the AFI-Net are the attention-guided feature enhancement and the boundary-aware saliency inference, where the attention module indicates salient objects coarsely, and the boundary information is used to equip the deep feature with more spatial details. Therefore, salient objects are well characterized, that is, well highlighted. The comprehensive experiments on five challenging public RGBD datasets clearly exhibit the superiority and effectiveness of the proposed AFI-Net.
本文提出了一种创新的RGB-D显著模型，即注意力引导特征集成网络，该网络可以提取和融合特征并进行显著性推理。具体来说，该模型首先提取多模态和多层次深度特征。然后，将一系列注意力模块应用于多层次的RGB和深度特征，从而产生增强的深度特征。接下来，对增强后的多模态深度特征进行分层融合。最后，将RGB和深度边界特征（即低级空间细节）添加到融合特征中以进行显著性推理。AFI-Net的关键点在于注意力引导的特征增强和边界感知显著性推理，其中注意力模块粗略地指示显著对象，边界信息用于为深度特征配备更多空间细节。因此，显著对象得到了很好的表征，即被很好地突出显示。在五个具有挑战性的公开RGB-D数据集上进行的综合实验清楚地展示了所提出的AFI-Net的优越性和有效性。
