# CLUENet: Cluster Attention Makes Neural Networks Have Eyes

Source: [CLUENet: Cluster Attention Makes Neural Networks Have Eyes](<https://www.sota2.com/research/paper/6937ad296cfd488761a4e9c4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-23T05:00:04.997Z

Authors: Xiangshuai Song, Jun-Jie Huang, Tianrui Liu, Ke Liang, Chang Tang

Published: 2025-12-06T08:26:36.000Z

## Abstract

Despite the success of convolution- and attention-based models in vision tasks, their rigid receptive fields and complex architectures limit their ability to model irregular spatial patterns and hinder interpretability, therefore posing challenges for tasks requiring high model transparency. Clustering paradigms offer promising interpretability and flexible semantic modeling, but suffer from limited accuracy, low efficiency, and gradient vanishing during training. To address these issues, we propose CLUster attEntion Network (CLUENet), an transparent deep architecture for visual semantic understanding. We propose three key innovations include (i) a Global Soft Aggregation and Hard Assignment with a Temperature-Scaled Cosin Attention and gated residual connections for enhanced local modeling, (ii) inter-block Hard and Shared Feature Dispatching, and (iii) an improved cluster pooling strategy. These enhancements significantly improve both classification performance and visual interpretability. Experiments on CIFAR-100 and Mini-ImageNet demonstrate that CLUENet outperforms existing clustering methods and mainstream visual models, offering a compelling balance of accuracy, efficiency, and transparency.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on ImageNet Mini](<https://www.sota2.com/research/sota/image-classification-on-imagenet-mini.md>): Image Classification; ImageNet mini; Top-1 Accuracy: 82.44.

- [Image Classification on CIFAR-100 (val)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-val.md>): Image Classification; CIFAR-100 (val); Accuracy: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2512.06345>)

[PDF](<https://arxiv.org/pdf/2512.06345.pdf>)