Exploring a Mixed Representation for Encoding Temporal Coherence

Guiding representation learning towards temporally stable features improves object identity encoding from video. Existing models have applied temporal coherence uniformly over all features based on the assumption that optimal object identity encoding only requires temporally stable components. We explore the effects of mixing temporally coherent invariant features alongside variable features in a single representation. Applying temporal coherence to different proportions of available features, we introduce a mixed representation autoencoder. Trained on several datasets, model outputs were passed to an object classification task to compare performance. Whilst the inclusion of temporal coherence improved object identity recognition in all cases, the majority of tests favoured a mixed representation.