Gabor filter incorporated CNN for compression
Akihiro Imamura, Nana Arizumi

TL;DR
This paper proposes incorporating learnable Gabor filters into CNNs to improve compression, reducing the number of kernels needed in early layers while maintaining performance.
Contribution
It introduces a method to embed Gabor filters into CNNs with learnable parameters, significantly reducing kernel count in early layers for efficient compression.
Findings
Gabor filters require fewer kernels than traditional CNN filters.
Significant kernel reduction achieved in early CNN layers.
Maintained or improved performance with fewer parameters.
Abstract
Convolutional neural networks (CNNs) are remarkably successful in many computer vision tasks. However, the high cost of inference is problematic for embedded and real-time systems, so there are many studies on compressing the networks. On the other hand, recent advances in self-attention models showed that convolution filters are preferable to self-attention in the earlier layers, which indicates that stronger inductive biases are better in the earlier layers. As shown in convolutional filters, strong biases can train specific filters and construct unnecessarily filters to zero. This is analogous to classical image processing tasks, where choosing the suitable filters makes a compact dictionary to represent features. We follow this idea and incorporate Gabor filters in the earlier layers of CNNs for compression. The parameters of Gabor filters are learned through backpropagation, so the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Neural Network Applications · Adversarial Robustness in Machine Learning · Domain Adaptation and Few-Shot Learning
MethodsConvolution
