Ro-SOS: Metric Expression Network (MEnet) for Robust Salient Object Segmentation
arXiv:1805.05638
Abstract
Although deep CNNs have brought significant improvement to image saliency detection, most CNN based models are sensitive to distortion such as compression and noise. In this paper, we propose an end-to-end generic salient object segmentation model called Metric Expression Network (MEnet) to deal with saliency detection with the tolerance of distortion. Within MEnet, a new topological metric space is constructed, whose implicit metric is determined by the deep network. As a result, we manage to group all the pixels in the observed image semantically within this latent space into two regions: a salient region and a non-salient region. With this architecture, all feature extractions are carried out at the pixel level, enabling fine granularity of output boundaries of the salient objects. What's more, we try to give a general analysis for the noise robustness of the network in the sense of Lipschitz and Jacobian literature. Experiments demonstrate that robust salient maps facilitating object segmentation can be generated by the proposed metric. Tests on several public benchmarks show that MEnet has achieved desirable performance. Furthermore, by direct computation and measuring the robustness, the proposed method outperforms previous CNN-based methods on distorted inputs.
arXiv commentThis version: 11 pages (12 with reference), 12 figures, 5 table; Version 1: 7 pages,7 figures, 4 tables; The paper for version 1 has been accepted by International Joint Conference on Artificial Intelligence (IJCAI),2018
References in corpus (5)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
- Semantic Instance Segmentation via Deep Metric Learning
- Image Quality Assessment Guided Deep Neural Networks Training