当前位置: X-MOL 学术IEEE Trans. Image Process. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Data-Level Recombination and Lightweight Fusion Scheme for RGB-D Salient Object Detection
IEEE Transactions on Image Processing ( IF 10.6 ) Pub Date : 2020-11-17 , DOI: 10.1109/tip.2020.3037470
Xuehao Wang , Shuai Li , Chenglizhao Chen , Yuming Fang , Aimin Hao , Hong Qin

Existing RGB-D salient object detection methods treat depth information as an independent component to complement RGB and widely follow the bistream parallel network architecture. To selectively fuse the CNN features extracted from both RGB and depth as a final result, the state-of-the-art (SOTA) bistream networks usually consist of two independent subbranches: one subbranch is used for RGB saliency, and the other aims for depth saliency. However, depth saliency is persistently inferior to the RGB saliency because the RGB component is intrinsically more informative than the depth component. The bistream architecture easily biases its subsequent fusion procedure to the RGB subbranch, leading to a performance bottleneck. In this paper, we propose a novel data-level recombination strategy to fuse RGB with D (depth) before deep feature extraction, where we cyclically convert the original 4-dimensional RGB-D into D GB, R D B and RG D . Then, a newly lightweight designed triple-stream network is applied over these novel formulated data to achieve an optimal channel-wise complementary fusion status between the RGB and D, achieving a new SOTA performance.

中文翻译:

用于RGB-D显着目标检测的数据级重组和轻量级融合方案

现有的RGB-D显着物体检测方法将深度信息作为独立的组件来补充RGB,并广泛遵循双流并行网络体系结构。为了有选择地融合从RGB和深度中提取的CNN特征作为最终结果,现有技术(SOTA)双流网络通常包含两个独立的子分支:一个子分支用于RGB显着性,另一个目标是深度显着。但是,深度显着性始终低于RGB显着性,因为RGB分量本质上比深度分量具有更多信息。双流体系结构很容易将其后续融合过程偏向RGB子分支,从而导致性能瓶颈。在本文中,我们提出了一种在深度特征提取之前将RGB与D(深度)融合的新型数据级重组策略,d GB,R d B和RG d 。然后,将新设计的轻量级三流网络应用于这些新颖的公式化数据,以实现RGB和D之间的最佳通道级互补融合状态,从而实现新的SOTA性能。
更新日期:2020-11-25
down
wechat
bug