Pyramid Feature Attention Network for Saliency detection

CVPR 2019  ·  Ting Zhao, Xiangqian Wu ·

Saliency detection is one of the basic challenges in computer vision. How to extract effective features is a critical point for saliency detection. Recent methods mainly adopt integrating multi-scale convolutional features indiscriminately. However, not all features are useful for saliency detection and some even cause interferences. To solve this problem, we propose Pyramid Feature Attention network to focus on effective high-level context features and low-level spatial structural features. First, we design Context-aware Pyramid Feature Extraction (CPFE) module for multi-scale high-level feature maps to capture rich context features. Second, we adopt channel-wise attention (CA) after CPFE feature maps and spatial attention (SA) after low-level feature maps, then fuse outputs of CA & SA together. Finally, we propose an edge preservation loss to guide network to learn more detailed information in boundary localization. Extensive evaluations on five benchmark datasets demonstrate that the proposed method outperforms the state-of-the-art approaches under different evaluation metrics.

PDF Abstract CVPR 2019 PDF CVPR 2019 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Saliency Detection DUT-OMRON Pyramid Feature Attention MAE 0.0414 # 1
Saliency Detection DUTS-test Pyramid Feature Attention MAE 0.0405 # 2
Saliency Detection ECSSD Pyramid Feature Attention MAE 0.0328 # 1
Saliency Detection HKU-IS Pyramid Feature Attention MAE 0.0324 # 2
Saliency Detection PASCAL-S Pyramid Feature Attention MAE 0.0677 # 1

Methods


No methods listed for this paper. Add relevant methods here