# The Master Key Filters Hypothesis: Deep Filters Are General

arXiv: https://arxiv.org/abs/2412.16751 · HTML: https://mlsanity.com/paper/2412.16751/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 32 references that are in the map.
- First posted on arXiv 21 Dec 2024.

## Builds on (most cited first, 19 of 19)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [Exploring Generalization in Deep Learning](https://mlsanity.com/paper/1706.08947/) (2017)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [Rethinking ImageNet Pre-training](https://mlsanity.com/paper/1811.08883/) (2018)
- [Understanding Neural Networks Through Deep Visualization](https://mlsanity.com/paper/1506.06579/) (2015)
- [Patches Are All You Need?](https://mlsanity.com/paper/2201.09792/) (2022)
- [HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions](https://mlsanity.com/paper/2207.14284/) (2022)
- [Initializing Models with Larger Ones](https://mlsanity.com/paper/2311.18823/) (2023)
- [On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification](https://mlsanity.com/paper/2106.07091/) (2021)
- [Covariance properties under natural image transformations for the generalized Gaussian derivative model for visual receptive fields](https://mlsanity.com/paper/2303.09803/) (2023)
- [Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels](https://mlsanity.com/paper/2401.14469/) (2024)
- [Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields](https://mlsanity.com/paper/2401.10178/) (2024)

## Built on by (most cited first, 3 of 3)

- [The Quest for Universal Master Key Filters in DS-CNNs](https://mlsanity.com/paper/2509.11711/) (2025)
- [Modelling and analysis of the 8 filters from the "master key filters hypothesis" for depthwise-separable deep networks in relation to idealized receptive fields based on scale-space theory](https://mlsanity.com/paper/2509.12746/) (2025)
- [Scale-invariant Gaussian derivative residual networks](https://mlsanity.com/paper/2603.02843/) (2026)

## Abstract (arXiv)

This paper challenges the prevailing view that convolutional neural network (CNN) filters become increasingly specialized in deeper layers. Motivated by recent observations of clusterable repeating patterns in depthwise separable CNNs (DS-CNNs) trained on ImageNet, we extend this investigation across various domains and datasets. Our analysis of DS-CNNs reveals that deep filters maintain generality, contradicting the expected transition to class-specific filters. We demonstrate the generalizability of these filters through transfer learning experiments, showing that frozen filters from models trained on different datasets perform well and can be further improved when sourced from larger datasets. Our findings indicate that spatial features learned by depthwise separable convolutions remain generic across all layers, domains, and architectures. This research provides new insights into the nature of generalization in neural networks, particularly in DS-CNNs, and has significant implications for transfer learning and model design.