Off-the-Shelf Deep Features for Saliency Detection

Abstract

Computational saliency refers to the ability to highlight the salient visual information for processing. The mechanism has proven to be helpful for human as well as computer vision. Computational saliency focuses on designing algorithms which, similarly to human vision, predict which regions in a scene are salient. Recently, salient object segmentation has introduced the use of object proposals. Object proposal methods provide image segments as proposals which can be used for saliency estimation. We propose several saliency features which are computed from different networks and different levels with the aim to define which optimal network and layer for the task of saliency detection. Also much recently, convolutional neural networks breakthroughs computer vision with the extraction of the much powerful features which are based on deep CNN. In this paper, we develop a saliency approach based on the computation of deep whitened features combined with shape features from object proposals. We train an SVM to predict the saliency of every object proposal. Experimental results shows that we outperform other state-of-the-art methods in PASCAL-S, FT, ECSSD, MSRA-B and ImgSal data sets in terms of F-score, PR curves. Furthermore, experiments show that applying whitening improve performance.

Cervical Cytology Classification Using PCA and GWO Enhanced Deep Features Selection

“…Before applying the PCA algorithm for feature dimension reduction, we need to perform data preprocessing that is required for the further steps. Depending upon the n-dimensional training set x (1) , x (2) , x (3) , … x (n) , we need to perform mean normalization or feature scaling similar to the supervised learning algorithms. The mean of each feature is computed as in Eq.…”

“…In this research, we extracted deep features [3] from pretrained convolution neural network (CNN) models and concatenated the features to form a large feature space. This is followed by the application of the principal component analysis (PCA) method for dimensionality reduction of the feature space, while keeping most of the important features intact, for which we retained 99% of the variance of the feature space.…”

Cervical Cytology Classification Using PCA & GWO Enhanced Deep Features Selection

“…Before applying the PCA algorithm for feature dimension reduction, we need to perform data preprocessing that is required for the further steps. Depending upon the n-dimensional training set x (1) , x (2) , x (3) , . .…”

“…In this research, we extracted deep features [3,5] from pre-trained CNN models and concatenated the features to form a large feature space. This is followed by the application of the Principal Component Analysis (PCA) method for dimensionality reduction of the feature space, while keeping most of the important features intact, for which we retained 99% of the variance of the feature space.…”