Estimating Classification Accuracy for Unlabeled Datasets Based on Block Scaling
Open Access
- 28 September 2023
- journal article
- research article
- Published by Taiwan Association of Engineering and Technology Innovation in International Journal of Engineering and Technology Innovation
- Vol. 13 (4) , 313-327
Abstract
This paper proposes an approach called block scaling quality (BSQ) for estimating the prediction accuracy of a deep network model. The basic operation perturbs the input spectrogram by multiplying all values within a block by , where is equal to 0 in the experiments. The ratio of perturbed spectrograms that have different prediction labels than the original spectrogram to the total number of perturbed spectrograms indicates how much of the spectrogram is crucial for the prediction. Thus, this ratio is inversely correlated with the accuracy of the dataset. The BSQ approach demonstrates satisfactory estimation accuracy in experiments when compared with various other approaches. When using only the Jamendo and FMA datasets, the estimation accuracy experiences an average error of 4.9% and 1.8%, respectively. Moreover, the BSQ approach holds advantages over some of the comparison counterparts. Overall, it presents a promising approach for estimating the accuracy of a deep network model.Keywords
This publication has 20 references indexed in Scilit:
- Research on Singing Voice Detection Based on a Long-Term Recurrent Convolutional Network with Vocal Separation and Temporal SmoothingElectronics, 2020
- Comparative study of singing voice detection based on deep neural networks and ensemble learningHuman-centric Computing and Information Sciences, 2018
- Estimating Prediction Qualities without Ground Truth: A Revisit of the Reverse Testing Framework2018
- Singing voice detection based on convolutional neural networks2018
- Linear regression analysis studyJournal of the Practice of Cardiovascular Sciences, 2018
- "Why Should I Trust You?"2016
- Melody Extraction from Polyphonic Music Signals: Approaches, applications, and challengesIEEE Signal Processing Magazine, 2014
- A Tandem Algorithm for Singing Pitch Extraction and Voice Separation From Music AccompanimentIEEE Transactions on Audio, Speech, and Language Processing, 2012
- Vocal detection in music with support vector machines2008
- Reverse testing2006