# Pre-processing and Compression: Understanding Hidden Representation Refinement Across Imaging Domains via Intrinsic Dimension

arXiv: https://arxiv.org/abs/2408.08381 · HTML: https://mlsanity.com/paper/2408.08381/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 34 references that are in the map.
- First posted on arXiv 15 Aug 2024.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [The Intrinsic Dimension of Images and Its Impact on Learning](https://mlsanity.com/paper/2104.08894/) (2021)
- [Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality](https://mlsanity.com/paper/1801.02613/) (2018)
- [Intrinsic dimension of data representations in deep neural networks](https://mlsanity.com/paper/1905.12784/) (2019)
- [Estimating the intrinsic dimension of datasets by a minimal neighborhood information](https://mlsanity.com/paper/1803.06992/) (2018)
- [Dimensionality-Driven Learning with Noisy Labels](https://mlsanity.com/paper/1806.02612/) (2018)
- [The geometry of hidden representations of large transformer models](https://mlsanity.com/paper/2302.00294/) (2023)
- [On the Intrinsic Dimensionality of Image Representations](https://mlsanity.com/paper/1803.09672/) (2018)
- [Automatic Knee Osteoarthritis Diagnosis from Plain Radiographs: A Deep Learning-Based Approach](https://mlsanity.com/paper/1710.10589/) (2017)
- [Geometry-Aware Maximum Likelihood Estimation of Intrinsic Dimension](https://mlsanity.com/paper/1904.06151/) (2019)
- [The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images](https://mlsanity.com/paper/2401.08865/) (2024)
- [The Intrinsic Manifolds of Radiological Images and their Role in Deep Learning](https://mlsanity.com/paper/2207.02797/) (2022)
- [Exploring the Representation Manifolds of Stable Diffusion Through the Lens of Intrinsic Dimension](https://mlsanity.com/paper/2302.09301/) (2023)

## Built on by (most cited first, 1 of 1)

- [Rethinking Intrinsic Dimension Estimation in Neural Representations](https://mlsanity.com/paper/2604.20276/) (2026)

## Abstract (arXiv)

In recent years, there has been interest in how geometric properties such as intrinsic dimension (ID) of a neural network's hidden representations change through its layers, and how such properties are predictive of important model behavior such as generalization ability. However, evidence has begun to emerge that such behavior can change significantly depending on the domain of the network's training data, such as natural versus medical images. Here, we further this inquiry by exploring how the ID of a network's learned representations changes through its layers, in essence, characterizing how the network successively refines the information content of input data to be used for predictions. Analyzing eleven natural and medical image datasets across six network architectures, we find that how ID changes through the network differs noticeably between natural and medical image models. Specifically, medical image models peak in representation ID earlier in the network, implying a difference in the image features and their abstractness that are typically used for downstream tasks in these domains. Additionally, we discover a strong correlation of this peak representation ID with the ID of the data in its input space, implying that the intrinsic information content of a model's learned representations is guided by that of the data it was trained on. Overall, our findings emphasize notable discrepancies in network behavior between natural and non-natural imaging domains regarding hidden representation information content, and provide further insights into how a network's learned features are shaped by its training data.