Enhancing the Performance of Image Classification Through Features Automatically Learned from Depth-Maps

Ciubotariu, George; Tomescu, Vlad-Ioan; Czibula, Gabriela

doi:10.1007/978-3-030-87156-7_6

Cited by 2 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another difficult dense prediction task is Depth Estimation (DE) [14], which is recognised in the literature as being illposed, since depth cannot be fully recovered from a single image without environment-specific assumptions. Compared to the previous one, this is often formulated as a regression problem, as the depth values are continuous, and they belong to a pre-determined interval [15], [16].…”

Section: A Selected Tasksmentioning

confidence: 99%

MBMT-Net: A Multi-Task Learning Based Convolutional Neural Network Architecture for Dense Prediction Tasks

Ciubotariu

Czibula

2022

IEEE Access

Self Cite

View full text Add to dashboard Cite

Recently proposed improvements in the field of Computer Vision refer to enhancing the feature processing capabilities of Single-Task Convolutional Neural Networks. A typical Single-Task network consists of a backbone and a head, where the feature extractor is usually optimised using the gradient provided by the head. Inevitably, the backbone specialises for the given task. This sort of approach does not scale well for learning multiple tasks at once while having the same input. As a response, there is an increasing interest in Multi-Task formulations. Since most Multi-Task architectures employ a single shared backbone, when gradients from different tasks are propagated back to it, it can result in its oversaturation. Thus, this problem may be solved using Multi-Backbone feature extractors. Hence, as a strategy proposed to compensate for these shortcomings, we introduce MBMT-Net, a Multi-Backbone-Multi-Task-Network architecture based on a development strategy that infuses backbones with more diverse and specialised processing capabilities. MBMT-Net consists of parallel pre-trained backbones whose outputs are concatenated and offered to the Multi-Task heads that shall benefit from richer and more diverse features with decreased number of network parameters when compared to traditional Multi-Task architectures. Our strategy is architecture independent, and it can be applied to different types of backbones and parsing heads, which greatly extends the domain of configurable features, finally enhancing existing Single-and Multi-Task model building strategies and outperforming them when using the Multi-Backbone design. As a result, while having a deficit of 12.16M parameters, MBMT-Net reaches state-of-the-art performances and surpasses the previously best semantic segmentation Multi-Task model in terms of Mean Intersection over Union when evaluated on NYUv2 data set.

show abstract

Section: A Selected Tasksmentioning

confidence: 99%

MBMT-Net: A Multi-Task Learning Based Convolutional Neural Network Architecture for Dense Prediction Tasks

Ciubotariu

Czibula

2022

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Applying data mining [1] techniques in order to extract meaningful knowledge from various data types is of great interest, being used for improving decision-making processes in various domains. Machine learning (ML) [2] offers a wide range of models and techniques for uncovering hidden patterns in data from numerous practical domains, such as bioinformatics (for protein dynamics analysis [3], [4]), mete-orology (for precipitation nowcasting and radar data analysis [5], [6]), software engineering (for software structure analysis [7] and restructuring [8], aspect mining [9]), medicine (for clinical decision support [10] and medical data analysis [11]), computer vision (for image analysis [12]), educational data mining (for academic data analysis [13], [14]), etc. Educational data mining (EDM) is a domain of research that applies data mining, ML, and statistics to data obtained from educational contexts.…”

Section: Introductionmentioning

confidence: 99%

IntelliDaM: A Machine Learning-Based Framework for Enhancing the Performance of Decision-Making Processes. A Case Study for Educational Data Mining

et al. 2022

Self Cite

View full text Add to dashboard Cite

Nowadays, both predictive and descriptive modelling play a key role in decision-making processes in almost every branch of activity. In this article we are introducing IntelliDaM , a generic machine learning-based framework useful for improving the performance of data mining tasks and subsequently enhancing decision-making processes. Through its components designed for feature analysis, unsupervised and supervised learning-based data mining, IntelliDaM facilitates hidden knowledge discovery from data. Intensive research has been conducted in the field of educational data mining, as education institutions are interested in constantly adapting their educational programs to the needs of society by improving the quality of managerial decisions, course instructors' decision-making, or information gathering for course design. The present work conducts a longitudinal educational data mining study by applying IntelliDaM to real data collected at Babeş-Bolyai University, Romania, for a Computer Science course. The problem of mining educational data has been thoroughly examined using the proposed framework, with the goal of analysing students' performance. A very good performance has been achieved for the classification task (an F 1 score of around 92%), and the results also highlighted a statistically significant performance improvement by using a technique for selecting discriminative data features. The performed study confirmed that IntelliDaM could be a useful instrument in educational environments, particularly for improving decision-making processes, like designing courses, the setup of efficient examinations, avoiding plagiarism, or offering support regarding stress management.INDEX TERMS Data mining, Educational data mining, Machine learning, Students' performance analysis and prediction.

show abstract

Enhancing the Performance of Image Classification Through Features Automatically Learned from Depth-Maps

Cited by 2 publications

References 12 publications

MBMT-Net: A Multi-Task Learning Based Convolutional Neural Network Architecture for Dense Prediction Tasks

MBMT-Net: A Multi-Task Learning Based Convolutional Neural Network Architecture for Dense Prediction Tasks

IntelliDaM: A Machine Learning-Based Framework for Enhancing the Performance of Decision-Making Processes. A Case Study for Educational Data Mining

Contact Info

Product

Resources

About