Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Mark Sandler

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


Jul 23, 2021
Andrey Zhmoginov, Dina Bashkirova, Mark Sandler


  Access Paper or Ask Questions

Meta-Learning Bidirectional Update Rules


Apr 10, 2021
Mark Sandler, Max Vladymyrov, Andrey Zhmoginov, Nolan Miller, Andrew Jackson, Tom Madams, Blaise Aguera y Arcas


  Access Paper or Ask Questions

Transfer Learning for Piano Sustain-Pedal Detection


Mar 24, 2021
Beici Liang, György Fazekas, Mark Sandler

* Published in 2019 International Joint Conference on Neural Networks (IJCNN) 

  Access Paper or Ask Questions

SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection


Jan 04, 2021
Keren Ye, Adriana Kovashka, Mark Sandler, Menglong Zhu, Andrew Howard, Marco Fornoni

* Accepted by the ACCV2020 (Oral) 

  Access Paper or Ask Questions

Large-Scale Generative Data-Free Distillation


Dec 10, 2020
Liangchen Luo, Mark Sandler, Zi Lin, Andrey Zhmoginov, Andrew Howard


  Access Paper or Ask Questions

Image segmentation via Cellular Automata


Aug 13, 2020
Mark Sandler, Andrey Zhmoginov, Liangcheng Luo, Alexander Mordvintsev, Ettore Randazzo, Blaise Agúera y Arcas


  Access Paper or Ask Questions

Structured Multi-Hashing for Model Compression


Nov 25, 2019
Elad Eban, Yair Movshovitz-Attias, Hao Wu, Mark Sandler, Andrew Poon, Yerlan Idelbayev, Miguel A. Carreira-Perpinan

* Elad and Yair contributed equally to the paper. They jointly proposed the idea of structured-multi-hashing. Elad: Wrote most of the code and ran most of the experiments Yair: Main contributor to the manuscript Hao: Coding and experiments Yerlan: Coding and experiments Miguel: advised Yerlan about optimization and model compression Mark:experiments Andrew: experiments 

  Access Paper or Ask Questions

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


Oct 17, 2019
Mark Sandler, Jonathan Baccash, Andrey Zhmoginov, Andrew Howard

* ICCV 2019 Workshop on Real-World Recognition from Low-Quality Images and Videos 

  Access Paper or Ask Questions

Adversarial Attacks in Sound Event Classification


Aug 15, 2019
Vinod Subramanian, Emmanouil Benetos, Ning Xu, SKoT McDonald, Mark Sandler

* Fixed Freesound data reference to FSDKaggle2018 

  Access Paper or Ask Questions

Information-Bottleneck Approach to Salient Region Discovery


Jul 22, 2019
Andrey Zhmoginov, Ian Fischer, Mark Sandler


  Access Paper or Ask Questions

Searching for MobileNetV3


May 14, 2019
Andrew Howard, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang, Yukun Zhu, Ruoming Pang, Vijay Vasudevan, Quoc V. Le, Hartwig Adam


  Access Paper or Ask Questions

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


Oct 25, 2018
Pramod Kaushik Mudrakarta, Mark Sandler, Andrey Zhmoginov, Andrew Howard


  Access Paper or Ask Questions

NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications


Sep 28, 2018
Tien-Ju Yang, Andrew Howard, Bo Chen, Xiao Zhang, Alec Go, Mark Sandler, Vivienne Sze, Hartwig Adam

* Accepted by ECCV 2018 

  Access Paper or Ask Questions

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


Jun 03, 2018
Keunwoo Choi, György Fazekas, Kyunghyun Cho, Mark Sandler

* 5 pages. EUSIPCO 2018 camera-ready. arXiv:1706.02361 does not have the overlapped part with this submission anymore 

  Access Paper or Ask Questions

A Tutorial on Deep Learning for Music Information Retrieval


May 03, 2018
Keunwoo Choi, György Fazekas, Kyunghyun Cho, Mark Sandler


  Access Paper or Ask Questions

MobileNetV2: Inverted Residuals and Linear Bottlenecks


Apr 02, 2018
Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen


  Access Paper or Ask Questions

CycleGAN, a Master of Steganography


Dec 16, 2017
Casey Chu, Andrey Zhmoginov, Mark Sandler

* NIPS 2017, workshop on Machine Deception 

  Access Paper or Ask Questions

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


Nov 14, 2017
Keunwoo Choi, George Fazekas, Kyunghyun Cho, Mark Sandler

* The section that overlapped with arXiv:1709.01922 is completely removed since the earlier version. This is the camera-ready version 

  Access Paper or Ask Questions

Transfer learning for music classification and regression tasks


Sep 13, 2017
Keunwoo Choi, György Fazekas, Mark Sandler, Kyunghyun Cho

* 18th International Society of Music Information Retrieval (ISMIR) Conference, Suzhou, China, 2017 

  Access Paper or Ask Questions

The Power of Sparsity in Convolutional Neural Networks


Feb 21, 2017
Soravit Changpinyo, Mark Sandler, Andrey Zhmoginov


  Access Paper or Ask Questions

Towards Music Captioning: Generating Music Playlist Descriptions


Jan 15, 2017
Keunwoo Choi, George Fazekas, Brian McFee, Kyunghyun Cho, Mark Sandler

* 2 pages, ISMIR 2016 Late-breaking/session extended abstract 

  Access Paper or Ask Questions

Convolutional Recurrent Neural Networks for Music Classification


Dec 21, 2016
Keunwoo Choi, George Fazekas, Mark Sandler, Kyunghyun Cho

* 5 pages, ICASSP 2017 submitted. Revised to fix previous CNN architectures and update experiment results 

  Access Paper or Ask Questions

Explaining Deep Convolutional Neural Networks on Music Classification


Jul 08, 2016
Keunwoo Choi, George Fazekas, Mark Sandler

* 7 pages, 10 figures 

  Access Paper or Ask Questions

Inverting face embeddings with convolutional neural networks


Jul 07, 2016
Andrey Zhmoginov, Mark Sandler


  Access Paper or Ask Questions

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


Jun 07, 2016
Keunwoo Choi, George Fazekas, Mark Sandler

* 4 pages, 2 figures, accepted to Workshop on Surprise, Opposition, and Obstruction in Adaptive and Personalized Systems (SOAP) 2016, Halifax, Canada 

  Access Paper or Ask Questions

Automatic tagging using deep convolutional neural networks


Jun 01, 2016
Keunwoo Choi, George Fazekas, Mark Sandler

* Accepted to ISMIR (International Society of Music Information Retrieval) Conference 2016 

  Access Paper or Ask Questions

Text-based LSTM networks for Automatic Music Composition


Apr 18, 2016
Keunwoo Choi, George Fazekas, Mark Sandler

* Accepted in the 1st Conference on Computer Simulation of Musical Creativity, 2016 

  Access Paper or Ask Questions