SEEK: A Framework of Superpixel Learning with CNN Features for Unsupervised Segmentation

Abstract

Supervised semantic segmentation algorithms have been a hot area of exploration recently, but now the attention is being drawn towards completely unsupervised semantic segmentation. In an unsupervised framework, neither the targets nor the ground truth labels are provided to the network. That being said, the network is unaware about any class instance or object present in the given data sample. So, we propose a convolutional neural network (CNN) based architecture for unsupervised segmentation. We used the squeeze and excitation network, due to its peculiar ability to capture the features’ interdependencies, which increases the network’s sensitivity to more salient features. We iteratively enable our CNN architecture to learn the target generated by a graph-based segmentation method, while simultaneously preventing our network from falling into the pit of over-segmentation. Along with this CNN architecture, image enhancement and refinement techniques are exploited to improve the segmentation results. Our proposed algorithm produces improved segmented regions that meet the human level segmentation results. In addition, we evaluate our approach using different metrics to show the quantitative outperformance.

DNA sequences performs as natural language processing by exploiting deep learning algorithm for the identification of N4-methylcytosine

“…Whereas, an assorted CNN model can be made by using handcrafted features. Convolution Neural Network has been utilized in several research areas such as image processing 39,40 , natural language processing 41 , and computational biology [42][43][44][45][46][47] . A grid search algorithm was implemented with different hyper-parameters values to obtain the most optimal CNN model during its learning.…”

DNC4mC-Deep: Identification and Analysis of DNA N4-Methylcytosine Sites Based on Different Encoding Schemes By Using Deep Learning

“…Additionally, a handy crafted feature can also be fed to CNN to build a heterogeneous model. A CNN has a big impact on various fields of natural language processing, image processing [53][54][55][56] and computational biology [57,58]. To get an optimum model we applied grid search and during learning the CNN, six hyperparameters were tuned.…”

iMethyl-Deep: N6 Methyladenosine Identification of Yeast Genome with Automatic Feature Extraction Technique by Using Deep Learning Algorithm

“…We presented a model based on a CNN instead of handcrafted features extraction models as a classifier such as support-vector machine (SVM) [17,[35][36][37]. CNN has been used in deep learning techniques and the area of bioinformatics extensively [33,34,[38][39][40] and also in other fields [41,42]. It has the ability to gather all the worthwhile features automatically from the RNA m6A sequences during the training process.…”