Unveiling The Unseen Identifiable Clusters In Trained Depthwise Convolutional Kernels
ASecurity**arXiv ID:** 2401.14469 **Authors:** Zahra Babaiee, Peyman M. Kiasari, Daniela Rus, Radu Grosu **Published:** 2024-01-25T19:05:53Z **Abstract:** Recent advances in depthwise-separable convolutional neural networks (DS-CNNs) have led to novel architectures, that surpass the performance of classical CNNs, by a considerable scalability and accuracy margin. This paper reveals another striking property of DS-CNN architectures: discernible and explainable patterns emerge in their trained depthwise...
- 3 stars
- 0 votes
- 0 copies
- 2 views
- Added September 11, 2026
Security analysis
100/100npx -y skills add hiyenwong/ai_collection --skill unveiling-the-unseen-identifiable-clusters-in-trained-depthwise-convolutional-kernels --agent claude-codeAre you the author of Unveiling The Unseen Identifiable Clusters In Trained Depthwise Convolutional Kernels?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-unveiling-the-unseen-identifiable-clusters-in-trai)# Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels
**arXiv ID:** 2401.14469
**Authors:** Zahra Babaiee, Peyman M. Kiasari, Daniela Rus, Radu Grosu
**Published:** 2024-01-25T19:05:53Z
**Abstract:**
Recent advances in depthwise-separable convolutional neural networks (DS-CNNs) have led to novel architectures, that surpass the performance of classical CNNs, by a considerable scalability and accuracy margin. This paper reveals another striking property of DS-CNN architectures: discernible and explainable patterns emerge in their trained depthwise convolutional kernels in all layers. Through an extensive analysis of millions of trained filters, with different sizes and from various models, we employed unsupervised clustering with autoencoders, to categorize these filters. Astonishingly, the patterns converged into a few main clusters, each resembling the difference of Gaussian (DoG) functions, and their first and second-order derivatives. Notably, we were able to classify over 95\% and 90\% of the filters from state-of-the-art ConvNextV2 and ConvNeXt models, respectively. This finding is not merely a technological curiosity; it echoes the foundational models neuroscientists have long proposed for the vision systems of mammals. Our results thus deepen our understanding of the emergent properties of trained DS-CNNs and provide a bridge between artificial and biological visual processing systems. More broadly, they pave the way for more interpretable and biologically-inspired neural network designs in the future.
## Skill Description
This skill is generated from the arXiv paper: Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels (2401.14469).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:2401.14469](http://arxiv.org/abs/2401.14469v1)
Attribution
Related skills
View all in tools →Comments
Loading comments…
Newsletter
Get the weekly list of safe new skills, and the ones we pulled.