A Deep Representation for Invariance And Music Classification

no code implementations • 1 Apr 2014 • Chiyuan Zhang, Georgios Evangelopoulos, Stephen Voinea, Lorenzo Rosasco, Tomaso Poggio

We present the main theoretical and computational aspects of a framework for unsupervised learning of invariant audio representations, empirically evaluated on music genre classification.

Classification General Classification +3

Learning An Invariant Speech Representation

no code implementations • 16 Jun 2014 • Georgios Evangelopoulos, Stephen Voinea, Chiyuan Zhang, Lorenzo Rosasco, Tomaso Poggio

Recognition of speech, and in particular the ability to generalize and learn from small sets of labelled examples like humans do, depends on an appropriate representation of the acoustic input.

General Classification Sound Classification +1

Discriminate-and-Rectify Encoders: Learning from Image Transformation Sets

no code implementations • 14 Mar 2017 • Andrea Tacchetti, Stephen Voinea, Georgios Evangelopoulos

We introduce a framework for weakly supervised learning of image embeddings that are robust to transformations and selective to the class distribution, using sets of transforming examples (orbit sets), deep parametrizations and a novel orbit-based loss.

Face Verification Object Recognition +2

Trading robust representations for sample complexity through self-supervised visual experience

no code implementations • NeurIPS 2018 • Andrea Tacchetti, Stephen Voinea, Georgios Evangelopoulos

Learning in small sample regimes is among the most remarkable features of the human perceptual system.

One-Shot Learning Representation Learning +1