Reverse Attention for Salient Object Detection (2018-07-26T00:00:00.000000Z)

TL;DR

An accurate yet compact deep network for efficient salient object detection that employs residual learning to learn side-output residual features for saliency refinement, which can be achieved with very limited convolutional parameters while keep accuracy.

Abstract

Benefit from the quick development of deep learning techniques, salient object detection has achieved remarkable progresses recently. However, there still exists following two major challenges that hinder its application in embedded devices, low resolution output and heavy model weight. To this end, this paper presents an accurate yet compact deep network for efficient salient object detection. More specifically, given a coarse saliency prediction in the deepest layer, we first employ residual learning to learn side-output residual features for saliency refinement, which can be achieved with very limited convolutional parameters while keep accuracy. Secondly, we further propose reverse attention to guide such side-output residual learning in a top-down manner. By erasing the current predicted salient regions from side-output features, the network can eventually explore the missing object parts and details which results in high resolution and accuracy. Experiments on six benchmark datasets demonstrate that the proposed approach compares favorably against state-of-the-art methods, and with advantages in terms of simplicity, efficiency (45 FPS) and model size (81 MB).

Authors

Shuhan Chen

2 papers

Xiuli Tan

2 papers

Benge Wang

2 papers

TL;DR

Abstract

Authors

References46 items

Deep Salient Object Detection With Dense Connections and Distraction Diagnosis

Squeeze-and-Excitation Networks

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

Learning Uncertain Convolutional Features for Accurate Saliency Detection

Non-local Deep Features for Salient Object Detection

Deep Level Sets for Salient Object Detection

Semantic Segmentation with Reverse Attention

Learning to Refine Object Contours with a Top-Down Fully Convolutional Encoder-Decoder Network

Residual Attention Network for Image Classification

Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution

Instance-Level Salient Object Segmentation

SRN: Side-Output Residual Network for Object Symmetry Detection in the Wild

Deeply Supervised Salient Object Detection with Short Connections

A Shape-Based Approach for Salient Object Detection Using Deep Learning

Saliency Detection with Recurrent Fully Convolutional Networks

DeepSkeleton: Learning Multi-Task Scale-Associated Deep Side Outputs for Object Skeleton Extraction in Natural Images

Visual Saliency Detection Based on Multiscale Deep CNN Features

Saliency Detection via Combining Region-Level and Pixel-Level Predictions with CNNs

DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection

Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation

Deep Saliency with Encoded Low Level Distance Map and High Level Features

Recurrent Attentional Networks for Saliency Detection

Hierarchical Image Saliency Detection on Extended CSSD

Learning to Refine Object Segments

Instance-Sensitive Fully Convolutional Networks

Deep Contrast Learning for Salient Object Detection

Deep Residual Learning for Image Recognition

Accurate Image Super-Resolution Using Very Deep Convolutional Networks

DISC: Deep Image Saliency Computing via Progressive Representation Learning

Attention to Scale: Scale-Aware Semantic Image Segmentation

DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection

STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation

U-Net: Convolutional Networks for Biomedical Image Segmentation

Holistically-Nested Edge Detection

Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

Salient Object Detection: A Benchmark

Fully convolutional networks for semantic segmentation

Very Deep Convolutional Networks for Large-Scale Image Recognition

Caffe: Convolutional Architecture for Fast Feature Embedding

The Secrets of Salient Object Segmentation

Salient Object Detection: A Discriminative Regional Feature Integration Approach

Saliency Detection via Graph-Based Manifold Ranking

Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials

Global contrast based salient region detection

Learning to Detect A Salient Object

A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names