b'Mark Sandler'

research

∙ 09/13/2023

Differentiable Modelling of Percussive Audio with Transient and Spectral Synthesis

Differentiable digital signal processing (DDSP) techniques, including me...

0 Jordie Shier, et al. ∙

research

∙ 09/11/2023

Uncovering mesa-optimization algorithms in Transformers

Transformers have become the dominant model in deep learning, but the re...

0 Johannes von Oswald, et al. ∙

research

∙ 05/24/2023

Interactive Neural Resonators

In this work, we propose a method for the controllable synthesis of real...

0 Rodrigo Díaz, et al. ∙

research

∙ 01/11/2023

Continual Few-Shot Learning Using HyperTransformers

We focus on the problem of learning without forgetting from multiple tas...

0 Max Vladymyrov, et al. ∙

research

∙ 01/05/2023

Training trajectories, mini-batch losses and the curious role of the learning rate

Stochastic gradient descent plays a fundamental role in nearly all appli...

0 Mark Sandler, et al. ∙

research

∙ 11/28/2022

Decentralized Learning with Multi-Headed Distillation

Decentralized learning with private data is a central problem in machine...

0 Andrey Zhmoginov, et al. ∙

research

∙ 10/27/2022

Rigid-Body Sound Synthesis with Differentiable Modal Resonators

Physical models of rigid bodies are used for sound synthesis in applicat...

0 Rodrigo Díaz, et al. ∙

research

∙ 08/12/2022

DDX7: Differentiable FM Synthesis of Musical Instrument Sounds

FM Synthesis is a well-known algorithm used to generate complex timbre f...

0 Franco Caspe, et al. ∙

research

∙ 07/15/2022

Anomalous behaviour in loss-gradient based interpretability methods

Loss-gradients are used to interpret the decision making process of deep...

0 Vinod Subramanian, et al. ∙

research

∙ 04/10/2022

Deep Conditional Representation Learning for Drum Sample Retrieval by Vocalisation

Imitating musical instruments with the human voice is an efficient way o...

0 Alejandro Delgado, et al. ∙

research

∙ 04/10/2022

Deep Embeddings for Robust User-Based Amateur Vocal Percussion Classification

Vocal Percussion Transcription (VPT) is concerned with the automatic det...

0 Alejandro Delgado, et al. ∙

research

∙ 03/29/2022

Fine-tuning Image Transformers using Learnable Memory

In this paper we propose augmenting Vision Transformer models with learn...

0 Mark Sandler, et al. ∙

research

∙ 01/11/2022

HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning

In this work we propose a HyperTransformer, a transformer-based model fo...

17 Andrey Zhmoginov, et al. ∙

research

∙ 10/18/2021

Learning Models for Query by Vocal Percussion: A Comparative Study

The imitation of percussive sounds via the human voice is a natural and ...

0 Alejandro Delgado, et al. ∙

research

∙ 07/23/2021

Compositional Models: Multi-Task Learning and Knowledge Transfer with Modular Networks

Conditional computation and modular networks have been recently proposed...

0 Andrey Zhmoginov, et al. ∙

research

∙ 04/10/2021

Meta-Learning Bidirectional Update Rules

In this paper, we introduce a new type of generalized neural network whe...

11 Mark Sandler, et al. ∙

research

∙ 03/24/2021

Transfer Learning for Piano Sustain-Pedal Detection

Detecting piano pedalling techniques in polyphonic music remains a chall...

0 Beici Liang, et al. ∙

research

∙ 01/04/2021

SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection

Deep learning based object detectors are commonly deployed on mobile dev...

1 Keren Ye, et al. ∙

research

∙ 12/10/2020

Large-Scale Generative Data-Free Distillation

Knowledge distillation is one of the most popular and effective techniqu...

4 Liangchen Luo, et al. ∙

research

∙ 08/11/2020

Image segmentation via Cellular Automata

In this paper, we propose a new approach for building cellular automata ...

28 Mark Sandler, et al. ∙

research

∙ 11/25/2019

Structured Multi-Hashing for Model Compression

Despite the success of deep neural networks (DNNs), state-of-the-art mod...

19 Elad Eban, et al. ∙

research

∙ 09/07/2019

Non-discriminative data or weak model? On the relative importance of data and model resolution

We explore the question of how the resolution of the input image ("input...

3 Mark Sandler, et al. ∙

research

∙ 07/22/2019

Information-Bottleneck Approach to Salient Region Discovery

We propose a new method for learning image attention masks in a semi-sup...

6 Andrey Zhmoginov, et al. ∙

research

∙ 07/04/2019

Adversarial Attacks in Sound Event Classification

Adversarial attacks refer to a set of methods that perturb the input to ...

0 Vinod Subramanian, et al. ∙

research

∙ 05/08/2019

Efficient On-line Computation of Visibility Graphs

A visibility algorithm maps time series into complex networks following ...

0 Benito García, et al. ∙

research

∙ 05/06/2019

Searching for MobileNetV3

We present the next generation of MobileNets based on a combination of c...

53 Andrew Howard, et al. ∙

research

∙ 03/05/2019

Visibility graphs for robust harmonic similarity measures between audio spectra

Graph theory is emerging as a new source of tools for time series analys...

0 Benito García, et al. ∙

research

∙ 10/25/2018

K For The Price Of 1: Parameter Efficient Multi-task And Transfer Learning

We introduce a novel method that enables parameter-efficient transfer an...

0 Pramod Kaushik Mudrakarta, et al. ∙

research

∙ 04/06/2018

Does k Matter? k-NN Hubness Analysis for Kernel Additive Modelling Vocal Separation

Kernel Additive Modelling (KAM) is a framework for source separation aim...

0 Benito García, et al. ∙

research

∙ 02/14/2018

Similarity measures for vocal-based drum sample retrieval using deep convolutional auto-encoders

The expressive nature of the voice provides a powerful medium for commun...

0 Adib Mehrabi, et al. ∙

research

∙ 01/13/2018

Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation

In this paper we describe a new mobile architecture, MobileNetV2, that i...

0 Mark Sandler, et al. ∙

research

∙ 01/13/2018

Inverted Residuals and Linear Bottlenecks: Mobile Networks forClassification, Detection and Segmentation

In this paper we describe a new mobile architecture, MobileNetV2, that i...

0 Mark Sandler, et al. ∙

research

∙ 12/08/2017

CycleGAN: a Master of Steganography

CycleGAN is one of the latest successful approaches to learn a correspon...

0 Casey Chu, et al. ∙

research

∙ 09/13/2017

A Tutorial on Deep Learning for Music Information Retrieval

Following their success in Computer Vision and other areas, deep learnin...

0 Keunwoo Choi, et al. ∙

research

∙ 09/06/2017

A Comparison on Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging

Deep neural networks (DNN) have been successfully applied for music clas...

0 Keunwoo Choi, et al. ∙

research

∙ 06/07/2017

The Effects of Noisy Labels on Deep Convolutional Neural Networks for Music Tagging

Deep neural networks (DNN) have been successfully applied to music class...

0 Keunwoo Choi, et al. ∙

research

∙ 03/27/2017

Transfer learning for music classification and regression tasks

In this paper, we present a transfer learning approach for music classif...

0 Keunwoo Choi, et al. ∙

research

∙ 02/21/2017

The Power of Sparsity in Convolutional Neural Networks

Deep convolutional networks are well-known for their high computational ...

0 Soravit Changpinyo, et al. ∙

research

∙ 09/14/2016

Convolutional Recurrent Neural Networks for Music Classification

We introduce a convolutional recurrent neural network (CRNN) for music t...

0 Keunwoo Choi, et al. ∙

research

∙ 08/17/2016

Towards Music Captioning: Generating Music Playlist Descriptions

Descriptions are often provided along with recommendations to help users...

0 Keunwoo Choi, et al. ∙

research

∙ 07/08/2016

Explaining Deep Convolutional Neural Networks on Music Classification

Deep convolutional neural networks (CNNs) have been actively adopted in ...

0 Keunwoo Choi, et al. ∙

research

∙ 06/14/2016

Inverting face embeddings with convolutional neural networks

Deep neural networks have dramatically advanced the state of the art for...

0 Andrey Zhmoginov, et al. ∙

research

∙ 06/07/2016

Towards Playlist Generation Algorithms Using RNNs Trained on Within-Track Transitions

We introduce a novel playlist generation algorithm that focuses on the q...

0 Keunwoo Choi, et al. ∙

Mark Sandler

Featured Co-authors