Rare-Aware Autoencoding: Reconstructing Spatially Imbalanced Data

• URL: http://arxiv.org/abs/2604.02031v1
• Date: Thu, 02 Apr 2026 13:38:29 GMT
• Title: Rare-Aware Autoencoding: Reconstructing Spatially Imbalanced Data
• Abstract summary: Autoencoders can be challenged by spatially non-uniform sampling of image content.<n>In practice, autoencoders are biased toward dominant patterns resulting in the loss of fine-grained detail.<n>We address spatial imbalance by two complementary components: (i) self-entropy-based loss that upweights statistically uncommon spatial locations.
• Score: 49.13338489780734
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• Impute-EM: Native Mixed-State Diffusion Models for Heterogeneous Data Imputation [71.74203645336385]
  Impute-EM alternates between imputing missing entries with the current model and refitting a diffusion backbone on completed data.<n>We characterize the update and show that the observed mask-indexed marginals match the targets at the limit.
  arXiv  Detail & Related papers  (2026-09-14T09:39:13Z)
• Limitations of Synthetic Data Generation in Specialized Data-Scarce Domains [11.861117372710714]
  This work focuses on domains where images differ substantially from common image datasets and additional data are expensive to obtain.<n>We evaluate the downstream performance improvements yielded by two schools of generative sparse data extension.<n>Across five trauma classification tasks using subject-wise train--validation splits, no generative approach consistently outperforms a strong non-generative baseline.
  arXiv  Detail & Related papers  (2026-08-13T19:43:31Z)
• SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation [62.55421542903781]
  We present textbfSpatialReward, a verifiable reward model explicitly designed to evaluate spatial layouts in generated images.<n>Experiments on Stable Diffusion and FLUX show that incorporating SpatialReward into RL training consistently improves spatial consistency and overall generation quality.
  arXiv  Detail & Related papers  (2026-03-23T17:26:35Z)
• More Data or Better Algorithms: Latent Diffusion Augmentation for Deep Imbalanced Regression [0.0]
  In many real-world regression tasks, the data distribution is heavily skewed, and models learn predominantly from abundant majority samples.<n>We propose LatentDiff, a novel framework that uses conditional diffusion models with priority-based generation to synthesize high-quality features in the latent representation space.<n>Experiments on three DIR benchmarks demonstrate substantial improvements in minority regions while maintaining overall accuracy.
  arXiv  Detail & Related papers  (2025-09-27T10:44:28Z)
• Error Distribution Smoothing:Advancing Low-Dimensional Imbalanced Regression [2.435853975142516]
  In real-world regression tasks, datasets frequently exhibit imbalanced distributions, characterized by a scarcity of data in high-complexity regions and an abundance in low-complexity areas.<n>We introduce a novel concept of Imbalanced Regression, which takes into account both the complexity of the problem and the density of data points, extending beyond traditional definitions that focus only on data density.<n>We propose Error Distribution Smoothing (EDS) as a solution to tackle imbalanced regression, effectively selecting a representative subset from the dataset to reduce redundancy while maintaining balance and representativeness.
  arXiv  Detail & Related papers  (2025-02-04T12:40:07Z)
• Re-Visible Dual-Domain Self-Supervised Deep Unfolding Network for MRI Reconstruction [48.30341580103962]
  We propose a novel re-visible dual-domain self-supervised deep unfolding network to address these issues.<n>We design a deep unfolding network based on Chambolle and Pock Proximal Point Algorithm (DUN-CP-PPA) to achieve end-to-end reconstruction.<n> Experiments conducted on the fastMRI and IXI datasets demonstrate that our method significantly outperforms state-of-the-art approaches in terms of reconstruction performance.
  arXiv  Detail & Related papers  (2025-01-07T12:29:32Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment [130.84010267004803]
  Training a generative adversarial network (GAN) with limited data has been a challenging task. A feasible solution is to start with a GAN well-trained on a large scale source domain and adapt it to the target domain with a few samples, termed as few shot generative model adaption. We propose a relaxed spatial structural alignment method to calibrate the target generative models during the adaption.
  arXiv  Detail & Related papers  (2022-03-06T14:26:25Z)
• Smoothing the Generative Latent Space with Mixup-based Distance Learning [32.838539968751924]
  We consider the situation where neither large scale dataset of our interest nor transferable source dataset is available. We propose latent mixup-based distance regularization on the feature space of both a generator and the counterpart discriminator.
  arXiv  Detail & Related papers  (2021-11-23T06:39:50Z)
• Spatially-Adaptive Image Restoration using Distortion-Guided Networks [51.89245800461537]
  We present a learning-based solution for restoring images suffering from spatially-varying degradations. We propose SPAIR, a network design that harnesses distortion-localization information and dynamically adjusts to difficult regions in the image.
  arXiv  Detail & Related papers  (2021-08-19T11:02:25Z)
• Towards Domain Invariant Single Image Dehazing [34.075765763305235]
  Presence of haze in images obscures underlying information, which is undesirable in applications requiring accurate environment information. In this paper, we utilize an encoder-decoder based network architecture to perform the task of dehazing.
  arXiv  Detail & Related papers  (2021-01-09T14:14:41Z)
• Unsupervised Metric Relocalization Using Transform Consistency Loss [66.19479868638925]
  Training networks to perform metric relocalization traditionally requires accurate image correspondences. We propose a self-supervised solution, which exploits a key insight: localizing a query image within a map should yield the same absolute pose, regardless of the reference image used for registration. We evaluate our framework on synthetic and real-world data, showing our approach outperforms other supervised methods when a limited amount of ground-truth information is available.
  arXiv  Detail & Related papers  (2020-11-01T19:24:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.