Related papers: Deep Unsupervised Drum Transcription

Neural networks trained on biased datasets tend to inadvertently learn spurious correlations, hindering generalization. We formally prove that (1) samples that exhibit spurious correlations lie on a lower rank manifold relative to the ones…

This work presents the first applications of self-supervised learning applied to data from digital antenna arrays. Encoder-decoder networks are pretrained on digital array data to perform a self-supervised noisy-reconstruction task called…

Deep neural networks often struggle to learn robust representations in the presence of dataset biases, leading to suboptimal generalization on unbiased datasets. This limitation arises because the models heavily depend on peripheral and…

Despite the success of deep learning in disparity estimation, the domain generalization gap remains an issue. We propose a semi-supervised pipeline that successfully adapts DispNet to a real-world domain by joint supervised training on…

In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for…

A key challenge in machine learning is to generalize from training data to an application domain of interest. This work generalizes the recently-proposed mixture invariant training (MixIT) algorithm to perform unsupervised learning in the…

Automatic music transcription (AMT) has achieved high accuracy for piano due to the availability of large, high-quality datasets such as MAESTRO and MAPS, but comparable datasets are not yet available for other instruments. In recent work,…

We propose a self-supervised representation learning model for the task of unsupervised phoneme boundary detection. The model is a convolutional neural network that operates directly on the raw waveform. It is optimized to identify spectral…

In recent years, many deep learning techniques for single-channel sound source separation have been proposed using recurrent, convolutional and transformer networks. When multiple microphones are available, spatial diversity between…

While great strides have been made in using deep learning algorithms to solve supervised learning tasks, the problem of unsupervised learning - leveraging unlabeled examples to learn about the structure of a domain - remains a difficult…

Several recent polyphonic music transcription systems have utilized deep neural networks to achieve state of the art results on various benchmark datasets, pushing the envelope on framewise and note-level performance measures. Unfortunately…

Deep neural networks have dramatically transformed machine learning, but their memory and energy demands are substantial. The requirements of real biological neural networks are rather modest in comparison, and one feature that might…

Current deep neural network based approaches to computed tomography (CT) metal artifact reduction (MAR) are supervised methods which rely heavily on synthesized data for training. However, as synthesized data may not perfectly simulate the…

Unsupervised cross-spectral stereo matching aims at recovering disparity given cross-spectral image pairs without any supervision in the form of ground truth disparity or depth. The estimated depth provides additional information…

We show how to train a fully convolutional neural network to perform inverse rendering from a single, uncontrolled image. The network takes an RGB image as input, regresses albedo and normal maps from which we compute lighting coefficients.…

Automatic music generation with artificial intelligence typically requires a large amount of data which is hard to obtain for many less common genres and musical instruments. To tackle this issue, we present ongoing work and preliminary…

Neural Networks accomplish amazing things, but they suffer from computational and memory bottlenecks that restrict their usage. Nowhere can this be better seen than in the mobile space, where specialized hardware is being created just to…

We propose a deep neural network architecture to infer dense depth from an image and a sparse point cloud. It is trained using a video stream and corresponding synchronized sparse point cloud, as obtained from a LIDAR or other range sensor,…

The human ability to track musical downbeats is robust to changes in tempo, and it extends to tempi never previously encountered. We propose a deterministic time-warping operation that enables this skill in a convolutional neural network…

While recent deep monocular depth estimation approaches based on supervised regression have achieved remarkable performance, costly ground truth annotations are required during training. To cope with this issue, in this paper we present a…