Rotationally Invariant Bark Recognition

Reměs, Václav; Haindl, Michal

doi:10.1007/978-3-319-97785-0_3

Cited by 5 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first row of Table 2 (NoDA), reports performance obtained by a ResNet50 without data augmentation. The last row of Table 2 (State of the art) reports the best performance reported in the literature on each of the three data sets using the same testing protocol used in this paper on the three data sets: the best for VIR is [33], for BARK [34], and for GRAV [12]). In [33], the best performance on VIR, features were extracted from the deeper layers of three pretrained CNNs (Densenet201, ResNet50, and GoogleNet), transformed into a deep co-occurrence representation [35], and trained on separate SVMs that were finally fused by sum rule.…”

Section: Preprints (Wwwpreprintsorg) | Not Peer-reviewed | Posted: 2 November 2021mentioning

confidence: 99%

“…Since the deeper layers of a CNN produce high-dimensional features, dimensionality reduction was performed using DCT [36]. In [34], the best performance on the Bark data set, a method based on 2D spiral Markovian texture features (2DSCAR) via multivariate Gaussian distribution was trained on a 1-NN with Jeffery's divergence as the distance measure. In [34], the best performance on GRAV, several ensembles were built from extracted views using a set of basic classifiers that included an SVM and two merge-view models proposed in [37].…”

Section: Preprints (Wwwpreprintsorg) | Not Peer-reviewed | Posted: 2 November 2021mentioning

confidence: 99%

See 1 more Smart Citation

Comparison of Different Image Data Augmentation Approaches

Nanni¹,

Paci²,

Brahnam³

et al. 2021

Preprint

View full text Add to dashboard Cite

Convolutional Neural Networks (CNNs) have gained prominence in the research literature on image classification over the last decade. One shortcoming of CNNs, however, is their lack of generalizability and tendency to overfit when presented with small training sets. Augmentation directly confronts this problem by generating new data points providing additional information. In this paper, we investigate the performance of more than ten different sets of data augmentation methods, with two novel approaches proposed here: one based on the Discrete Wavelet Transform and the other on the Constant-Q Gabor transform. Pretrained ResNet50 networks are finetuned on each augmentation method. Combinations of these networks are evaluated and compared across three benchmark data sets of images representing diverse problems and collected by instruments that capture information at different scales: a virus data set, a bark data set, and a LIGO glitches data set. Experiments demonstrate the superiority of this approach. The best ensemble proposed in this work achieves state-of-the-art performance across all three data sets. This result shows that varying data augmentation is a feasible way for building an ensemble of classifiers for image classification (code available at https://github.com/LorisNanni).

show abstract

Section: Preprints (Wwwpreprintsorg) | Not Peer-reviewed | Posted: 2 November 2021mentioning

confidence: 99%

Section: Preprints (Wwwpreprintsorg) | Not Peer-reviewed | Posted: 2 November 2021mentioning

confidence: 99%

Comparison of Different Image Data Augmentation Approaches

Nanni¹,

Paci²,

Brahnam³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The first row of Table 2 (NoDA), reports performance obtained by a ResNet50 without data augmentation. The last row of Table 2 (State of the art) reports the best performance reported in the literature on each of the data sets: VIR [46], BARK [47], GRAV [17], and POR [15]). In [46], which reports the best performance on VIR, features were extracted from the deeper layers of three pretrained CNNs (Densenet201, ResNet50, and GoogleNet), transformed into a deep co-occurrence representation [48] and trained on separate SVMs that were finally fused by sum rule.…”

mentioning

confidence: 99%

“…As the deeper layers of a CNN produce high-dimensional features, dimensionality reduction was performed using DCT [49]. In [47], which obtains the best performance on the BARK data set, a method based on 2D spiral Markovian texture features (2DSCAR) via multivariate Gaussian distribution was trained on a 1-NN with Jeffery's divergence as the distance measure. In [47], which provides the best performance on GRAV, several ensembles were built from extracted views using a set of basic classifiers that included an SVM and two merge-view models proposed in [50].…”

mentioning

confidence: 99%

Comparison of Different Image Data Augmentation Approaches

et al. 2021

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) have gained prominence in the research literature on image classification over the last decade. One shortcoming of CNNs, however, is their lack of generalizability and tendency to overfit when presented with small training sets. Augmentation directly confronts this problem by generating new data points providing additional information. In this paper, we investigate the performance of more than ten different sets of data augmentation methods, with two novel approaches proposed here: one based on the discrete wavelet transform and the other on the constant-Q Gabor transform. Pretrained ResNet50 networks are finetuned on each augmentation method. Combinations of these networks are evaluated and compared across four benchmark data sets of images representing diverse problems and collected by instruments that capture information at different scales: a virus data set, a bark data set, a portrait dataset, and a LIGO glitches data set. Experiments demonstrate the superiority of this approach. The best ensemble proposed in this work achieves state-of-the-art (or comparable) performance across all four data sets. This result shows that varying data augmentation is a feasible way for building an ensemble of classifiers for image classification.

show abstract

Feature transforms for image data augmentation

Nanni

Paci

Brahnam

et al. 2022

Neural Comput & Applic

View full text Add to dashboard Cite

A problem with convolutional neural networks (CNNs) is that they require large datasets to obtain adequate robustness; on small datasets, they are prone to overfitting. Many methods have been proposed to overcome this shortcoming with CNNs. In cases where additional samples cannot easily be collected, a common approach is to generate more data points from existing data using an augmentation technique. In image classification, many augmentation approaches utilize simple image manipulation algorithms. In this work, we propose some new methods for data augmentation based on several image transformations: the Fourier transform (FT), the Radon transform (RT), and the discrete cosine transform (DCT). These and other data augmentation methods are considered in order to quantify their effectiveness in creating ensembles of neural networks. The novelty of this research is to consider different strategies for data augmentation to generate training sets from which to train several classifiers which are combined into an ensemble. Specifically, the idea is to create an ensemble based on a kind of bagging of the training set, where each model is trained on a different training set obtained by augmenting the original training set with different approaches. We build ensembles on the data level by adding images generated by combining fourteen augmentation approaches, with three based on FT, RT, and DCT, proposed here for the first time. Pretrained ResNet50 networks are finetuned on training sets that include images derived from each augmentation method. These networks and several fusions are evaluated and compared across eleven benchmarks. Results show that building ensembles on the data level by combining different data augmentation methods produce classifiers that not only compete competitively against the state-of-the-art but often surpass the best approaches reported in the literature.

show abstract

Rotationally Invariant Bark Recognition

Cited by 5 publications

References 15 publications

Comparison of Different Image Data Augmentation Approaches

Comparison of Different Image Data Augmentation Approaches

Comparison of Different Image Data Augmentation Approaches

Feature transforms for image data augmentation

Contact Info

Product

Resources

About