Corpus ID: 14155902

A Deep Learning Based Fast Image Saliency Detection Algorithm

  title={A Deep Learning Based Fast Image Saliency Detection Algorithm},
  author={Hengyue Pan and Hui Jiang},
In this paper, we propose a fast deep learning method for object saliency detection using convolutional neural networks. [...] Key Method In our approach, we use a gradient descent method to iteratively modify the input images based on the pixel-wise gradients to reduce a pre-defined cost function, which is defined to measure the class-specific objectness and clamp the class-irrelevant outputs to maintain image background. The pixel-wise gradients can be efficiently computed using the back-propagation algorithm…Expand
Deep Convolutional Network Based Saliency Prediction for Retrieval of Natural Images
The method uses the visual attention model to extract the saliency map of a given image with the help of SalNet algorithm and the results show that the proposed method is efficient and accurate compared to other previously existed models. Expand
Distinct Class-Specific Saliency Maps for Weakly Supervised Semantic Segmentation
A weakly supervised semantic segmentation method which is based on CNN-based class-specific saliency maps and fully-connected CRF and has outperformed state-of-the-art results with the PASCAL VOC 2012 dataset under the weakly-supervised setting. Expand
Supervised adversarial networks for image saliency detection
  • H. Pan, H. Jiang
  • Computer Science, Engineering
  • International Conference on Graphic and Image Processing
  • 2020
This paper proposes a novel model for image saliency detection, which is called Supervised Adversarial Networks (SAN), however, different from GAN, the proposed method uses fully supervised learning to learn both G-Network and D-Network by applying class labels of the training set. Expand
A comprehensive review of recent advances on deep vision systems
A recent survey of the state-of-the-art DL platforms and architectures used for deep vision systems describes the architecture of various DL models such as AutoEncoders, deep Boltzmann machines, convolution neural networks, recurrent neural networks and deep residual learning. Expand
Weakly Supervised Summarization of Web Videos
Casting the problem as a weakly supervised learning problem, this work proposes a flexible deep 3D CNN architecture to learn the notion of importance using only video-level annotation, and without any human-crafted training data. Expand
Automatic Attribute Discovery with Neural Activations
An automatic approach to discover and analyze visual attributes from a noisy collection of image-text data on the Web based on the relationship between attributes and neural activations in the deep network is proposed. Expand
Meticulous Transparency - An Evaluation Process for an Agile AI Regulatory Scheme
A new ethical evaluation framework for usage by future regulators: Meticulous Transparency (MT) is outlined, which allows regulators to keep pace with technological progress by evaluating AI applications for their capabilities and the intentionality of developers. Expand


Saliency detection by multi-context deep learning
This paper proposes a multi-context deep learning framework for salient object detection that employs deep Convolutional Neural Networks to model saliency of objects in images and investigates different pre-training strategies to provide a better initialization for training the deep neural networks. Expand
Superpixel based color contrast and color distribution driven salient object detection
This paper designs a comprehensive salient object detection system which takes the advantages of color contrast together with color distribution and outputs high quality saliency maps and outperforms 8 state-of-the-art methods. Expand
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Expand
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
This paper addresses the visualisation of image classification models, learnt using deep Convolutional Networks (ConvNets), and establishes the connection between the gradient-based ConvNet visualisation methods and deconvolutional networks. Expand
Probabilistic Multi-Task Learning for Visual Saliency Estimation in Video
This work proposes a multi-task learning algorithm to learn the task-related “stimulus-saliency” mapping functions for each scene, which learns various fusion strategies, which are used to integrate the stimulus-driven and task- related components to obtain the visual saliency. Expand
Global contrast based salient region detection
This work proposes a regional contrast based saliency extraction algorithm, which simultaneously evaluates global contrast differences and spatial coherence, and consistently outperformed existing saliency detection methods. Expand
Very Deep Convolutional Networks for Large-Scale Image Recognition
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. Expand
Saliency Detection: A Boolean Map Approach
A novel Boolean Map based Saliency model, based on a Gestalt principle of figure-ground segregation, that consistently achieves state-of-the-art performance compared with ten leading methods on five eye tracking datasets. Expand
ImageNet classification with deep convolutional neural networks
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective. Expand
Salient Object Detection: A Benchmark
This work analyzes benchmark datasets and scoring techniques and provides a quantitative comparison of 35 state-of-the-art saliency detection models to identify the scenes where models or humans fail to detect the most salient object. Expand