Decontextualized learning for interpretable hierarchical representations of visual patterns
This addresses the need for interpretable features in scientific research using imaging data, though it appears incremental as it builds on existing generative and ladder network methods.
The paper tackles the problem of obtaining interpretable hierarchical features from small natural image datasets for scientific analysis, presenting Decontextualized Hierarchical Representation Learning (DHRL) which achieves disentangled and generative representations applicable to evolutionary biology.
Apart from discriminative models for classification and object detection tasks, the application of deep convolutional neural networks to basic research utilizing natural imaging data has been somewhat limited; particularly in cases where a set of interpretable features for downstream analysis is needed, a key requirement for many scientific investigations. We present an algorithm and training paradigm designed specifically to address this: decontextualized hierarchical representation learning (DHRL). By combining a generative model chaining procedure with a ladder network architecture and latent space regularization for inference, DHRL address the limitations of small datasets and encourages a disentangled set of hierarchically organized features. In addition to providing a tractable path for analyzing complex hierarchal patterns using variation inference, this approach is generative and can be directly combined with empirical and theoretical approaches. To highlight the extensibility and usefulness of DHRL, we demonstrate this method in application to a question from evolutionary biology.