On Orthogonal Projections for Dimension Reduction and Applications in Augmented Target Loss Functions for Learning Problems

2019 11th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)

et al. 2019

Convolutional neural network (CNN) architectures have originated and revolutionized machine learning for images. In order to take advantage of CNNs in predictive modeling with audio data, standard FFT-based signal processing methods are often applied to convert the raw audio waveforms into an image-like representations (e.g. spectrograms). Even though conventional images and spectrograms differ in their feature properties, this kind of pre-processing reduces the amount of training data necessary for successful training. In this contribution we investigate how input and target representations interplay with the amount of available training data in a music information retrieval setting. We compare the standard mel-spectrogram inputs with a newly proposed representation, called Mel scattering. Furthermore, we investigate the impact of additional target data representations by using an augmented target loss function which incorporates unused available information. We observe that all proposed methods outperform the standard mel-transform representation when using a limited data set and discuss their strengths and limitations. The source code for reproducibility of our experiments as well as intermediate results and model checkpoints are available in an online repository.

Section: Augmented Target Loss Functionmentioning

confidence: 99%

Section: Augmented Target Loss Functionmentioning

confidence: 99%

Section: Augmented Target Loss Functionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving Machine Hearing on Limited Data Sets

Harár

Bammer

2019 11th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)

et al. 2019

“…The CNN is trained using high quality and coregistered anatomical and dMRI data (from the HCP), and then predicts tissue segmentation of new subjects directly from dMRI data, without the need for anatomical MRI data nor inter-modality registration. To further improve accuracy we trained the CNN using a novel augmented target loss function (Breger et al, 2020) that penalizes segmentation errors in tissue boundary regions. The dMRI input includes seven DKI and DTI parameter maps that have been corrected for implausible values using MK-Curve and three additional MK-Curve-derived maps (Zhang et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Based Segmentation of Brain Tissue from Diffusion MRI

Zhang

Cho

et al. 2020

Preprint

Segmentation of brain tissue types from diffusion MRI (dMRI) is an important task, required for quantification of brain microstructure and for improving tractography. Current dMRI segmentation is mostly based on anatomical MRI (e.g., T1- and T2-weighted) segmentation that is registered to the dMRI space. However, such inter-modality registration is challenging due to more image distortions and lower image resolution in the dMRI data as compared with the anatomical MRI data. In this study, we present a deep learning method that learns tissue segmentation from high-quality imaging datasets from the Human Connectome Project (HCP), where registration of anatomical data to dMRI is more precise. The method is then able to predict a tissue segmentation directly from new dMRI data, including data collected with a different acquisition protocol, without requiring anatomical data and inter-modality registration. We train a convolutional neural network (CNN) to learn a tissue segmentation model using a novel augmented target loss function designed to improve accuracy in regions of tissue boundary. To further improve accuracy, our method adds diffusion kurtosis imaging (DKI) parameters that characterize non-Gaussian water molecule diffusion to the conventional diffusion tensor imaging parameters. The DKI parameters are calculated from the recently proposed mean-kurtosis-curve method that corrects implausible DKI parameter values and provides additional features that discriminate between tissue types. We demonstrate high tissue segmentation accuracy on HCP data, and also when applying the HCP-trained model on dMRI data from a clinical acquisition with lower resolution and fewer gradient directions.

An Amplified-Target Loss Approach for Photoreceptor Layer Segmentation in Pathological OCT Scans

Orlando

Lecture Notes in Computer Science

Bogunović

et al. 2019

Segmenting anatomical structures such as the photoreceptor layer in retinal optical coherence tomography (OCT) scans is challenging in pathological scenarios. Supervised deep learning models trained with standard loss functions are usually able to characterize only the most common disease appearance from a training set, resulting in suboptimal performance and poor generalization when dealing with unseen lesions. In this paper we propose to overcome this limitation by means of an augmented target loss function framework. We introduce a novel amplified-target loss that explicitly penalizes errors within the central area of the input images, based on the observation that most of the challenging disease appearance is usually located in this area. We experimentally validated our approach using a data set with OCT scans of patients with macular diseases. We observe increased performance compared to the models that use only the standard losses. Our proposed loss function strongly supports the segmentation model to better distinguish photoreceptors in highly pathological scenarios. equal contribution arXiv:1908.00764v2 [eess.IV]