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

Autor: Hyongsuk Kim, Abbas Khan, Muhammad Umraiz, Talha Ilyas
Jazyk: angličtina
Rok vydání: 2020
Předmět:
Computer Networks and Communications
Computer science
lcsh:TK7800-8360
02 engineering and technology
Convolutional neural network
03 medical and health sciences
0202 electrical engineering
electronic engineering
information engineering
Segmentation
segmentation refinement
image enhancement
Electrical and Electronic Engineering
squeeze and excitation network
030304 developmental biology
0303 health sciences
Ground truth
resnet
business.industry
lcsh:Electronics
k-means clustering
Pattern recognition
Object (computer science)
Class (biology)
ComputingMethodologies_PATTERNRECOGNITION
Hardware and Architecture
Control and Systems Engineering
Salient
Signal Processing
unsupervised segmentation
Graph (abstract data type)
020201 artificial intelligence & image processing
Artificial intelligence
business
Zdroj: Electronics
Volume 9
Issue 3
Electronics, Vol 9, Iss 3, p 383 (2020)
ISSN: 2079-9292
DOI: 10.3390/electronics9030383
Popis: 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&rsquo
interdependencies, which increases the network&rsquo
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.
Databáze: OpenAIRE
Externí odkaz: