U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection

Published in

Pattern Recognition(2020)

External Links:

Generate Graph DownloadPDF

TL;DR

A simple yet powerful deep network architecture, U2-Net, for salient object detection (SOD), a two-level nested U-structure that enables us to train a deep network from scratch without using backbones from image classification tasks.

Authors

Xuebin Qin

5 papers

Masood Dehghan

3 papers

Martin Jägersand

4 papers

Osmar R Zaiane

4 papers

Chenyang Huang

2 papers

References59 items

Salient object detection employing a local tree-structured low-rank representation and foreground consistency

Deep Embedding Features for Salient Object Detection

A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision

Attentive Feedback Network for Boundary-Aware Salient Object Detection

CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detection

U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection

Published in

Pattern Recognition(2020)

External Links:

Generate Graph DownloadPDF

TL;DR

Authors

Xuebin Qin

5 papers

Masood Dehghan

3 papers

Martin Jägersand

4 papers

Osmar R Zaiane

4 papers

Chenyang Huang

2 papers

References59 items

Salient object detection employing a local tree-structured low-rank representation and foreground consistency

Deep Embedding Features for Salient Object Detection

A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision

Attentive Feedback Network for Boundary-Aware Salient Object Detection

CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detection

BASNet: Boundary-Aware Salient Object Detection

A Simple Pooling-Based Design for Real-Time Salient Object Detection

Cascaded Partial Decoder for Fast and Accurate Salient Object Detection

Multi-Source Weak Supervision for Saliency Detection

Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation

Quantized Densely Connected U-Nets for Efficient Landmark Localization

CU-Net: Coupled U-Nets

Reverse Attention for Salient Object Detection

R³Net: Recurrent Residual Refinement Network for Saliency Detection

A Bi-Directional Message Passing Model for Salient Object Detection

Progressive Attention Guided Recurrent Network for Salient Object Detection

Detect Globally, Refine Locally: A Novel Approach to Saliency Detection

DocUNet: Document Image Unwarping via a Stacked U-Net

Recurrently Aggregating Deep Features for Salient Object Detection

Material based salient object detection from hyperspectral images

Salient Object Detection by Lossless Feature Reflection

Automatic differentiation in PyTorch

A Stagewise Refinement Model for Detecting Salient Objects in Images

PiCANet: Learning Pixel-Wise Contextual Attention for Saliency Detection

Learning Uncertain Convolutional Features for Accurate Saliency Detection

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

Structure-Measure: A New Way to Evaluate Foreground Maps

Learning to Detect Salient Objects with Image-Level Supervision

Non-local Deep Features for Salient Object Detection

A novel graph-based optimization framework for salient object detection

Pyramid Scene Parsing Network

Aggregated Residual Transformations for Deep Neural Networks

Deeply Supervised Salient Object Detection with Short Connections

Visual Saliency Detection Based on Multiscale Deep CNN Features

Densely Connected Convolutional Networks

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

Stacked Hourglass Networks for Human Pose Estimation

Deep Residual Learning for Image Recognition

U-Net: Convolutional Networks for Biomedical Image Segmentation

Holistically-Nested Edge Detection

Salient Object Detection: A Benchmark

Adam: A Method for Stochastic Optimization

Fully convolutional networks for semantic segmentation

Going deeper with convolutions

Very Deep Convolutional Networks for Large-Scale Image Recognition

How to Evaluate Foreground Maps

The Secrets of Salient Object Segmentation

Hierarchical Saliency Detection

Saliency Detection via Graph-Based Manifold Ranking

ImageNet classification with deep convolutional neural networks

Saliency Modeling from Image Histograms

Design and perceptual validation of performance measures for salient object segmentation

Understanding the difficulty of training deep feedforward neural networks

ImageNet: A large-scale hierarchical image database

Frequency-tuned salient region detection

Relaxed Precision and Recall for Ontology Matching

Image Analysis Using Mathematical Morphology

Robust and Efficient Saliency Modeling from Image Co-Occurrence Histograms

Detect Globally, Reﬁne Locally: A Novel Approach to Saliency Detection

Field of Study

Computer Science

Journal Information

Name

Pattern Recognit.

Page

158-172

Volume

Venue Information

Name

Pattern Recognition

Type

journal

URL

http://www.elsevier.com/wps/find/journaldescription.cws_home/328/description#description

Alternate Names

Pattern Recognit