# HPFF: Hierarchical Locally Supervised Learning with Patch Feature Fusion

Source: [HPFF: Hierarchical Locally Supervised Learning with Patch Feature Fusion](<https://www.sota2.com/research/paper/68fa74041e209131cea5f3e3>)

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

Data updated: 2025-10-26T03:00:03.231Z

Authors: Junhao Su, Chenghao He, Feiyu Zhu, Xiaojie Xu, Dongzhi Guan, Chenyang Si

Published: 2024-07-08T06:05:19.000Z

## Abstract

Traditional deep learning relies on end-to-end backpropagation for training, but it suffers from drawbacks such as high memory consumption and not aligning with biological neural networks. Recent advancements have introduced locally supervised learning, which divides networks into modules with isolated gradients and trains them locally. However, this approach can lead to performance lag due to limited interaction between these modules, and the design of auxiliary networks occupies a certain amount of GPU memory. To overcome these limitations, we propose a novel model called HPFF that performs hierarchical locally supervised learning and patch-level feature computation on the auxiliary networks. Hierarchical Locally Supervised Learning (HiLo) enables the network to learn features at different granularity levels along their respective local paths. Specifically, the network is divided into two-level local modules: independent local modules and cascade local modules. The cascade local modules combine two adjacent independent local modules, incorporating both updates within the modules themselves and information exchange between adjacent modules. Patch Feature Fusion (PFF) reduces GPU memory usage by splitting the input features of the auxiliary networks into patches for computation. By averaging these patch-level features, it enhances the network's ability to focus more on those patterns that are prevalent across multiple patches. Furthermore, our method exhibits strong generalization capabilities and can be seamlessly integrated with existing techniques. We conduct experiments on CIFAR-10, STL-10, SVHN, and ImageNet datasets, and the results demonstrate that our proposed HPFF significantly outperforms previous approaches, consistently achieving state-of-the-art performance across different datasets. Our code is available at: https://github.com/Zeudfish/HPFF.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2407.05638>)

[PDF](<https://arxiv.org/pdf/2407.05638.pdf>)
