# UPANets: Learning from the Universal Pixel Attention Networks

Source: [UPANets: Learning from the Universal Pixel Attention Networks](<https://www.sota2.com/research/paper/68fa6d741e209131cea3a0a9>)

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

Data updated: 2025-12-14T18:40:03.517Z

Authors: Ching-Hsun Tseng, Shin-Jye Lee, Jia-Nan Feng, Shengzhong Mao, Yu-Ping Wu, Jia-Yu Shang, Mou-Chung Tseng, Xiao-Jun Zeng

Published: 2021-03-15T18:27:59.000Z

## Abstract

Among image classification, skip and densely-connection-based networks have dominated most leaderboards. Recently, from the successful development of multi-head attention in natural language processing, it is sure that now is a time of either using a Transformer-like model or hybrid CNNs with attention. However, the former need a tremendous resource to train, and the latter is in the perfect balance in this direction. In this work, to make CNNs handle global and local information, we proposed UPANets, which equips channel-wise attention with a hybrid skip-densely-connection structure. Also, the extreme-connection structure makes UPANets robust with a smoother loss landscape. In experiments, UPANets surpassed most well-known and widely-used SOTAs with an accuracy of 96.47% in Cifar-10, 80.29% in Cifar-100, and 67.67% in Tiny Imagenet. Most importantly, these performances have high parameters efficiency and only trained in one customer-based GPU. We share implementing code of UPANets in https://github.com/hanktseng131415go/UPANets.

## 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/2103.08640>)

[PDF](<https://arxiv.org/pdf/2103.08640.pdf>)