Contextual Encoder-Decoder Network for Visual Saliency Prediction (2019-02-18T00:00:00.000000Z)

TL;DR

This work proposes an approach based on a convolutional neural network pre-trained on a large-scale image classification task that achieves competitive and consistent results across multiple evaluation metrics on two public saliency benchmarks and demonstrates the effectiveness of the suggested approach on five datasets and selected examples.

Authors

Alexander Kroner

1 papers

M. Senden

1 papers

K. Driessens

1 papers

R. Goebel

1 papers

TL;DR

Authors

References64 items

Running Large-Scale Simulations on the Neurorobotics Platform to Understand Vision – The Case of Visual Crowding

Invariance Analysis of Saliency Models versus Human Gaze During Scene Free Viewing

Saliency Prediction in the Deep Learning Era: An Empirical Investigation

Saliency Prediction in the Deep Learning Era: Successes, Limitations, and Future Challenges

Influence of Image Classification Accuracy on Saliency Map Estimation

Places: A 10 Million Image Database for Scene Recognition

EML-NET: An Expandable Multi-Layer NETwork for Saliency Prediction

Dual Path Networks

Rethinking Atrous Convolution for Semantic Image Segmentation

Saliency Revisited: Analysis of Mouse Movements Versus Fixations

Saliency Benchmarking Made Easy: Separating Models, Maps and Metrics

SalGAN: Visual Saliency Prediction with Generative Adversarial Networks

Predicting Human Eye Fixations via an LSTM-Based Saliency Attentive Model

Emergence of foveal image sampling from learning to attend in visual scenes

Deconvolution and Checkerboard Artifacts

A Deep Spatial Contextual Long-Term Recurrent Convolutional Network for Saliency Detection

DeepGaze II: Reading fixations from deep features trained on object recognition

A deep multi-level network for saliency prediction

Densely Connected Convolutional Networks

The Interaction Between Vision and Eye Movements †

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

End-to-End Saliency Mapping via Probability Distribution Prediction

What Do Different Evaluation Metrics Tell Us About Saliency Models?

SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks

Multi-Scale Context Aggregation by Dilated Convolutions

DeepFix: A Fully Convolutional Neural Network for Predicting Human Eye Fixations

SALICON: Saliency in Context

CAT2000: A Large Scale Fixation Dataset for Boosting Saliency Research

TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking

Adam: A Method for Stochastic Optimization

Hypercolumns for object segmentation and fine-grained localization

Fully convolutional networks for semantic segmentation

Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet

Very Deep Convolutional Networks for Large-Scale Image Recognition

Large-Scale Optimization of Hierarchical Features for Saliency Prediction in Natural Images

The Secrets of Salient Object Segmentation

Predicting human gaze beyond pixels.

Saliency and Human Fixations: State-of-the-Art and Study of Comparison Metrics

DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

Saliency Detection via Graph-Based Manifold Ranking

On the importance of initialization and momentum in deep learning

ImageNet classification with deep convolutional neural networks

A Benchmark of Computational Models of Saliency to Predict Human Fixations

Object-based attentional selection in scene viewing.

Understanding the difficulty of training deep feedforward neural networks

Faces and text attract gaze independent of the task: Experimental data and computer model.

Learning to predict where humans look

ImageNet: A large-scale hierarchical image database

Objects predict fixations better than early saliency.

SUN: A Bayesian framework for saliency using natural statistics.

Saliency Detection: A Spectral Residual Approach

Graph-Based Visual Saliency

Contextual guidance of eye movements and attention in real-world scenes: the role of global features in object search.

The general inefficiency of batch training for gradient descent learning

The Cost of Cortical Computation

A Model of Saliency-Based Visual Attention for Rapid Scene Analysis

Information integration across saccadic eye movements

Integrating visual information from successive fixations.

A feature-integration theory of attention

Grating visibility as a function of orientation and retinal eccentricity

MIT saliency benchmark

ORIENTING OF ATTENTION *

Human cortical magnification factor and its relation to visual acuity

Shifts in selective visual attention: towards the underlying neural circuitry.

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL

Alternate Names