34 citations · 72 across the 4 of their papers we have counts for
4 papers
Powers of layers for image-to-image translation
Hugo Touvron, Matthijs Douze, Matthieu Cord +1
We propose a simple architecture to address unpaired image-to-image translation tasks: style or class transfer, denoising, deblurring, deblocking, etc. We start from an image autoe…
Radioactive data: tracing through training
Alexandre Sablayrolles, Matthijs Douze, Cordelia Schmid +1
We want to detect whether a particular image dataset has been used to train a model. We propose a new technique, \emph{radioactive data}, that makes imperceptible changes to this d…
Lead2Gold: Towards exploiting the full potential of noisy transcriptions for speech recognition
Adrien Dufraux, Emmanuel Vincent, Awni Hannun +2
The transcriptions used to train an Automatic Speech Recognition (ASR) system may contain errors. Usually, either a quality control stage discards transcriptions with too many erro…
MultiGrain: a unified image embedding for classes and instances
Maxim Berman, Hervé Jégou, Andrea Vedaldi +2
MultiGrain is a network architecture producing compact vector representations that are suited both for image classification and particular object retrieval. It builds on a standard…