Beyond one-hot encoding: Lower dimensional target embedding

作者：Rodriguez Pau^*; Bautista Miguel A; Gonzalez Jordi; Escalera Sergio

来源：Image and Vision Computing, 2018, 75: 21-31.

DOI：10.1016/j.imavis.2018.04.004

• Error correcting output codes
• Output embeddings
• Deep learning
• Computer vision

Target encoding plays a central role when learning Convolutional Neural Networks. In this realm, one-hot encoding is the most prevalent strategy due to its simplicity. However, this so widespread encoding schema assumes a flat label space, thus ignoring rich relationships existing among labels that can be exploited during training. In large-scale datasets, data does not span the full label space, but instead lies in a low-dimensional output manifold. Following this observation, we embed the targets into a low-dimensional space, drastically improving convergence speed while preserving accuracy. Our contribution is two fold: (i) We show that random projections of the label space are a valid tool to find such lower dimensional embeddings, boosting dramatically convergence rates at zero computational cost; and (ii) we propose a normalized eigenrepresentation of the class manifold that encodes the targets with minimal information loss, improving the accuracy of random projections encoding while enjoying the same convergence rates. Experiments on CIFAR-100, CUB200-2011, Imagenet, and MIT Places demonstrate that the proposed approach drastically improves convergence speed while reaching very competitive accuracy rates.

• 出版日期2018-7