# Decontextualized learning for interpretable hierarchical representations of visual patterns

Source: [Decontextualized learning for interpretable hierarchical representations of visual patterns](<https://www.sota2.com/research/paper/68fa5f081e209131ce9e71a7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T19:06:52.680Z

Authors: R. Ian Etheredge, Manfred Schartl, Alex Jordan

Published: 2020-08-31T14:47:55.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2009.09893>)

[PDF](<https://arxiv.org/pdf/2009.09893.pdf>)
