# Many Perception Tasks are Highly Redundant Functions of their Input Data

arXiv: https://arxiv.org/abs/2407.13841 · HTML: https://mlsanity.com/paper/2407.13841/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 107 references that are in the map.
- First posted on arXiv 18 Jul 2024.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [Optimization Methods for Large-Scale Machine Learning](https://mlsanity.com/paper/1606.04838/) (2016)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks](https://mlsanity.com/paper/1901.08584/) (2019)
- [Benign Overfitting in Linear Regression](https://mlsanity.com/paper/1906.11300/) (2019)
- [Making Convolutional Networks Shift-Invariant Again](https://mlsanity.com/paper/1904.11486/) (2019)
- [The Intrinsic Dimension of Images and Its Impact on Learning](https://mlsanity.com/paper/2104.08894/) (2021)
- [Emergence of Invariance and Disentanglement in Deep Representations](https://mlsanity.com/paper/1706.01350/) (2017)
- [Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning](https://mlsanity.com/paper/1810.01075/) (2018)
- [Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates](https://mlsanity.com/paper/1708.07120/) (2017)
- [Towards Understanding the Spectral Bias of Deep Learning](https://mlsanity.com/paper/1912.01198/) (2019)
- [Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regression](https://mlsanity.com/paper/2012.01536/) (2020)
- [Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction](https://mlsanity.com/paper/2006.08558/) (2020)
- [Rethinking Vision Transformers for MobileNet Size and Speed](https://mlsanity.com/paper/2212.08059/) (2022)
- [AudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmark](https://mlsanity.com/paper/1807.03418/) (2018)
- [Learning by Reconstruction Produces Uninformative Features For Perception](https://mlsanity.com/paper/2402.11337/) (2024)
- [Model Zoo: A Growing "Brain" That Learns Continually](https://mlsanity.com/paper/2106.03027/) (2021)
- [FFCV: Accelerating Training by Removing Data Bottlenecks](https://mlsanity.com/paper/2306.12517/) (2023)
- [Efficient Estimation of Mutual Information for Strongly Dependent Variables](https://mlsanity.com/paper/1411.2003/) (2014)
- [Beyond Normal: On the Evaluation of Mutual Information Estimators](https://mlsanity.com/paper/2306.11078/) (2023)
- [Diving into the shallows: a computational perspective on large-scale shallow learning](https://mlsanity.com/paper/1703.10622/) (2017)
- [Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representations](https://mlsanity.com/paper/2303.03307/) (2023)

## Built on by (most cited first, 4 of 4)

- [LayerLock: Non-collapsing Representation Learning with Progressive Freezing](https://mlsanity.com/paper/2509.10156/) (2025)
- [From Linearity to Non-Linearity: How Masked Autoencoders Capture Spatial Correlations](https://mlsanity.com/paper/2508.15404/) (2025)
- [An Analytical Characterization of Sloppiness in Neural Networks: Insights from Linear Models](https://mlsanity.com/paper/2505.08915/) (2025)
- [OctoSense: Self-Supervised Learning for Multimodal Robot Perception](https://mlsanity.com/paper/2606.27317/) (2026)

## Abstract (arXiv)

We show that many perception tasks, from visual recognition, semantic segmentation, optical flow, depth estimation to vocalization discrimination, are highly redundant functions of their input data. Images or spectrograms, projected into different subspaces, formed by orthogonal bases in pixel, Fourier or wavelet domains, can be used to solve these tasks remarkably well regardless of whether it is the top subspace where data varies the most, some intermediate subspace with moderate variability--or the bottom subspace where data varies the least. This phenomenon occurs because different subspaces have a large degree of redundant information relevant to the task.