paper-with-me

Papers

Connections Between Pairs of Filters Improve the Accuracy of Convolutional Neural Networks

2026-06-11 · Kathleen Anderson, Philipp Grüning, Erhardt Barth arxiv

While researchers continue to find new and improved network structures for CNNs, most of the newly invented architectures still rely on the traditional pattern of stacking convolutional blocks and separating them with pointwise activation functions. However, there are drawbacks to a network purely building on pointwise nonlinearities. One alternative is to introduce a pairwise connection between two filters of a network. Typical connection functions use multiplications or the minimum operation to realize logical AND connections. In this paper, we go one step further by demonstrating that CNNs can benefit from more general connections, which include parameters that are learned. With such parameters, the network is able to implement different connections in different network layers and better adapt the connection function to the task at hand.

📄 PDF Abstract BibTeX arXiv:2606.13736

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DiracNets: Training Very Deep Neural Networks Without Skip-Connections

2017-06-01 · Sergey Zagoruyko, Nikos Komodakis

Deep neural networks with skip-connections, such as ResNet, show excellent performance in various image classification benchmarks. It is though observed that the initial motivation behind them - training deeper networks …

image-classificationImage Classification

Deep Expander Networks: Efficient Deep Networks from Graph Theory

2017-11-23 · ECCV 2018 9 · Ameya Prabhu, Girish Varma, Anoop Namboodiri

Efficient CNN designs like ResNets and DenseNet were proposed to improve accuracy vs efficiency trade-offs. They essentially increased the connectivity, allowing efficient information flow across layers. Inspired by thes…

The 'tree-dependent components' of natural scenes are edge filters

2009-12-01 · NeurIPS 2009 12 · Daniel Zoran, Yair Weiss

We propose a new model for natural image statistics. Instead of minimizing dependency between components of natural images, we maximize a simple form of dependency in the form of tree-dependency. By learning filters and …

Form

HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations

2025-10-13 · Shuaicheng Zhang, Haohui Wang, Junhong Lin, Xiaojie Guo 외 arxiv

Graph heterophily, where connected nodes have different labels, has attracted significant interest recently. Most existing works adopt a simplified approach - using low-pass filters for homophilic graphs and high-pass fi…

Natural Questions

Error Feedback Approach for Quantization Noise Reduction of Distributed Graph Filters

2024-12-07 · Xue Xian Zheng, Tareq Al-Naffouri

This work introduces an error feedback approach for reducing quantization noise of distributed graph filters. It comes from error spectrum shaping techniques from state-space digital filters, and therefore establishes co…

Quantization