# Constrained Linear Data-feature Mapping for Image Classification

Source: [Constrained Linear Data-feature Mapping for Image Classification](<https://www.sota2.com/research/paper/68fa57151e209131ce9a2412>)

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

Data updated: 2025-10-27T05:13:50.940Z

Authors: Juncai He, Yuyan Chen, Lian Zhang, Jinchao Xu

Published: 2019-11-23T22:39:47.000Z

## Abstract

In this paper, we propose a constrained linear data-feature mapping model as an interpretable mathematical model for image classification using convolutional neural network (CNN) such as the ResNet. From this viewpoint, we establish the detailed connections in a technical level between the traditional iterative schemes for constrained linear system and the architecture for the basic blocks of ResNet. Under these connections, we propose some natural modifications of ResNet type models which will have less parameters but still maintain almost the same accuracy as these corresponding original models. Some numerical experiments are shown to demonstrate the validity of this constrained learning data-feature mapping assumption.

## 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/1911.10428>)

[PDF](<https://arxiv.org/pdf/1911.10428.pdf>)