Odd-One-Out Representation Learning
arXiv:2012.07966
Abstract
The effective application of representation learning to real-world problems requires both techniques for learning useful representations, and also robust ways to evaluate properties of representations. Recent work in disentangled representation learning has shown that unsupervised representation learning approaches rely on fully supervised disentanglement metrics, which assume access to labels for ground-truth factors of variation. In many real-world cases ground-truth factors are expensive to collect, or difficult to model, such as for perception. Here we empirically show that a weakly-supervised downstream task based on odd-one-out observations is suitable for model selection by observing high correlation on a difficult downstream abstract visual reasoning task. We also show that a bespoke metric-learning VAE model which performs highly on this task also out-performs other standard unsupervised and a weakly-supervised disentanglement model across several metrics.
References in corpus (11)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Recent Advances in Autoencoder-Based Representation Learning
- Adaptively Learning the Crowd Kernel
- Measuring abstract reasoning in neural networks
- Weakly-Supervised Disentanglement Without Compromises
- Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies
- Bayesian representation learning with oracle constraints
- Disentangling Factors of Variation Using Few Labels
- Unsupervised Model Selection for Variational Disentangled Representation Learning
- Understanding Visual Concepts with Continuation Learning
- TVAE: Triplet-Based Variational Autoencoder using Metric Learning