Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection

Abstract

Fully convolutional neural networks (FCNs) have shown outstanding performance in many dense labeling problems. One key pillar of these successes is mining relevant information from features in convolutional layers. However, how to better aggregate multi-level convolutional feature maps for salient object detection is underexplored. In this work, we present Amulet, a generic aggregating multi-level convolutional feature framework for salient object detection. Our framework first integrates multi-level feature maps into multiple resolutions, which simultaneously incorporate coarse semantics and fine details. Then it adaptively learns to combine these feature maps at each resolution and predict saliency maps with the combined features. Finally, the predicted results are efficiently fused to generate the final saliency map. In addition, to achieve accurate boundary inference and semantic enhancement, edge-aware feature maps in low-level layers and the predicted results of low resolution features are recursively embedded into the learning framework. By aggregating multi-level convolutional features in this efficient and flexible manner, the proposed saliency model provides accurate salient object labeling. Comprehensive experiments demonstrate that our method performs favorably against state-of-the art approaches in terms of near all compared evaluation metrics.

Accepted as a poster in ICCV 2017, including 10 pages, 5 figures and 2 tables

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Residual Learning for Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Fully Convolutional Networks for Semantic Segmentation
• Learning Deconvolution Network for Semantic Segmentation
• DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
• Visual Saliency Based on Multiscale Deep Features
• Show and Tell: A Neural Image Caption Generator
• What is a salient object? A dataset and a baseline model for salient object detection
• Deep Contrast Learning for Salient Object Detection
• Understanding Deep Image Representations by Inverting Them
• Instance-sensitive Fully Convolutional Networks

Cited by in corpus (16)

• Direction-aware Spatial Context Features for Shadow Detection
• How Much Position Information Do Convolutional Neural Networks Encode?
• Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
• PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection
• Camouflaged Object Segmentation with Distraction Mining
• Agile Amulet: Real-Time Salient Object Detection with Contextual Attention
• Selectivity or Invariance: Boundary-aware Salient Object Detection
• Learning Synergistic Attention for Light Field Salient Object Detection
• Semantics Meet Saliency: Exploring Domain Affinity and Models for Dual-Task Prediction
• Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object Segmentation
• Depth Quality-Inspired Feature Manipulation for Efficient RGB-D Salient Object Detection
• BiconNet: An Edge-preserved Connectivity-based Approach for Salient Object Detection
• Exploiting the Value of the Center-dark Channel Prior for Salient Object Detection
• Image Smoothing via Unsupervised Learning
• Hi-Fi: Hierarchical Feature Integration for Skeleton Detection
• Deep attention-guided fusion network for lesion segmentation