Related papers: Data Augmentation for Drum Transcription with Conv…
In the process of recording, storage and transmission of time-domain audio signals, errors may be introduced that are difficult to correct in an unsupervised way. Here, we train a convolutional deep neural network to re-synthesize input…
Current work in named entity recognition (NER) shows that data augmentation techniques can produce more robust models. However, most existing techniques focus on augmenting in-domain data in low-resource scenarios where annotated data is…
Deep learning techniques are often criticized to heavily depend on a large quantity of labeled data. This problem is even more challenging in medical image analysis where the annotator expertise is often scarce. We propose a novel…
We examine the role of memorization in deep learning, drawing connections to capacity, generalization, and adversarial robustness. While deep networks are capable of memorizing noise data, our results suggest that they tend to prioritize…
We propose a novel method for Acoustic Event Detection (AED). In contrast to speech, sounds coming from acoustic events may be produced by a wide variety of sources. Furthermore, distinguishing them often requires analyzing an extended time…
Data, algorithms, and arithmetic power are the three foundational conditions for deep learning to be effective in the application domain. Data is the focus for developing deep learning algorithms. In practical engineering applications, some…
In recent years, deep learning technique has received intense attention owing to its great success in image recognition. A tendency of adaption of deep learning in various information processing fields has formed, including music…
Deep convolutional neural networks have driven substantial advancements in the automatic understanding of images. Requiring a large collection of images and their associated annotations is one of the main bottlenecks limiting the adoption…
Model pruning has become a useful technique that improves the computational efficiency of deep learning, making it possible to deploy solutions in resource-limited scenarios. A widely-used practice in relevant work assumes that a…
Deep Neural Networks (DNNs) have been shown to be susceptible to memorization or overfitting in the presence of noisily-labelled data. For the problem of robust learning under such noisy data, several algorithms have been proposed. A…
The customizable nature of deep learning models have allowed them to be successful predictors in various disciplines. These models are often trained with respect to thousands or millions of instances for complicated problems, but the…
Data augmentations are important ingredients in the recipe for training robust neural networks, especially in computer vision. A fundamental question is whether neural network features encode data augmentation transformations. To answer…
With the increasing utilization of deep learning in outdoor settings, its robustness needs to be enhanced to preserve accuracy in the face of distribution shifts, such as compression artifacts. Data augmentation is a widely used technique…
Convolutional Neural Networks (CNNs) serve as the workhorse of deep learning, finding applications in various fields that rely on images. Given sufficient data, they exhibit the capacity to learn a wide range of concepts across diverse…
The classification of acoustic environments allows for machines to better understand the auditory world around them. The use of deep learning in order to teach machines to discriminate between different rooms is a new area of research.…
Data augmentation is commonly used to encode invariances in learning methods. However, this process is often performed in an inefficient manner, as artificial examples are created by applying a number of transformations to all points in the…
Generative convolutional deep neural networks, e.g. popular GAN architectures, are relying on convolution based up-sampling methods to produce non-scalar outputs like images or video sequences. In this paper, we show that common up-sampling…
In today's world, a vast amount of data is being generated by edge devices that can be used as valuable training data to improve the performance of machine learning algorithms in terms of the achieved accuracy or to reduce the compute…
Modern neural networks are usually highly over-parameterized. Behind the wide usage of over-parameterized networks is the belief that, if the data are simple, then the trained network will be automatically equivalent to a simple predictor.…
Various data augmentation techniques have been recently proposed in image-based deep reinforcement learning (DRL). Although they empirically demonstrate the effectiveness of data augmentation for improving sample efficiency or…