Rare-Aware Autoencoding: Reconstructing Spatially Imbalanced Data

TL;DR

This paper introduces a novel autoencoding method that addresses spatial data imbalance by emphasizing rare spatial features, leading to improved reconstruction quality in diverse real-world datasets.

Contribution

It proposes a self-entropy-based loss and a sample propagation mechanism to enhance autoencoder performance on spatially imbalanced data, a challenge in many scientific imaging domains.

Findings

Outperforms existing methods on simulated and real datasets with spatial imbalance.

Improves reconstruction consistency and detail preservation for rare spatial features.

Demonstrates effectiveness across physical, biological, and astronomical imaging data.

Abstract

Autoencoders can be challenged by spatially non-uniform sampling of image content. This is common in medical imaging, biology, and physics, where informative patterns occur rarely at specific image coordinates, as background dominates these locations in most samples, biasing reconstructions toward the majority appearance. In practice, autoencoders are biased toward dominant patterns resulting in the loss of fine-grained detail and causing blurred reconstructions for rare spatial inputs especially under spatial data imbalance. We address spatial imbalance by two complementary components: (i) self-entropy-based loss that upweights statistically uncommon spatial locations and (ii) Sample Propagation, a replay mechanism that selectively re-exposes the model to hard to reconstruct samples across batches during training. We benchmark existing data balancing strategies, originally developed for supervised classification, in the unsupervised reconstruction setting. Drawing on the limitations of these approaches, our method specifically targets spatial imbalance by encouraging models to focus on statistically rare locations, improving reconstruction consistency compared to existing baselines. We validate in a simulated dataset with controlled spatial imbalance conditions, and in three, uncontrolled, diverse real-world datasets spanning physical, biological, and astronomical domains. Our approach outperforms baselines on various reconstruction metrics, particularly under spatial imbalance distributions. These results highlight the importance of data representation in a batch and emphasize rare samples in unsupervised image reconstruction. We will make all code and related data available.