On the Impact of Labeled Sample Selection in Semisupervised Learning for Complex Visual Recognition Tasks

Abstract

One of the most important aspects in semisupervised learning is training set creation among a limited amount of labeled data in such a way as to maximize the representational capability and efficacy of the learning framework. In this paper, we scrutinize the effectiveness of different labeled sample selection approaches for training set creation, to be used in semisupervised learning approaches for complex visual pattern recognition problems. We propose and explore a variety of combinatory sampling approaches that are based on sparse representative instances selection (SMRS), OPTICS algorithm, k-means clustering algorithm, and random selection. These approaches are explored in the context of four semisupervised learning techniques, i.e., graph-based approaches (harmonic functions and anchor graph), low-density separation, and smoothness-based multiple regressors, and evaluated in two real-world challenging computer vision applications: image-based concrete defect recognition on tunnel surfaces and video-based activity recognition for industrial workflow monitoring.

A Machine Learning Based Classification Method for Customer Experience Survey Analysis

“…It firstly extracts a set of appropriate features from the raw data, by applying convolutions on the input signals propagating them into deep layers while at the last layer a classification is carried out to assign the input data into classes but on the use of the deep features identified by the convolutional layers. CNNs utilize trainable filters and pooling operations on their input resulting in a hierarchy of increasingly complex features [25,60,61]. Convolutional layers consist of a rectangular grid of neurons (filters), each of which takes inputs from rectangular sections of the previous layer.…”

Multiclass Confusion Matrix Reduction Method and Its Application on Net Promoter Score Classification Problem

“…It firstly extracts a set of appropriate features from the raw data, by applying convolutions on the input signals propagating them into deep layers while at the last layer a classification is carried out to assign the input data into classes but on the use of the deep features identified by the convolutional layers. CNNs utilize trainable filters and pooling operations on their input resulting in a hierarchy of increasingly complex features [31][32][33]. Convolutional layers consist of a rectangular grid of neurons (filters), each of which takes inputs from rectangular sections of the previous layer.…”

Semi-supervised Fine-Tuning for Deep Learning Models in Remote Sensing Applications

“…Towards that direction two approaches gained interest past years: a) SSL and b) tensor-based learning. The former [22] employ graph-based approaches, as in [23] that are not scalable and co-trained or are prone to errors induced by wrong predictions between the models [24]. The latter tensor case is not useful if the amount of data exceeds a threshold [25].…”