# Mimicking Ensemble Learning with Deep Branched Networks

Source: [Mimicking Ensemble Learning with Deep Branched Networks](<https://www.sota2.com/research/paper/68fa631d1e209131ce9fce29>)

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

Data updated: 2025-10-25T20:33:20.017Z

Authors: Byungju Kim, Youngsoo Kim, Yeakang Lee, Junmo Kim

Published: 2017-02-21T13:33:37.000Z

## Abstract

This paper proposes a branched residual network for image classification. It is known that high-level features of deep neural network are more representative than lower-level features. By sharing the low-level features, the network can allocate more memory to high-level features. The upper layers of our proposed network are branched, so that it mimics the ensemble learning. By mimicking ensemble learning with single network, we have achieved better performance on ImageNet classification task.

## 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/1702.06376>)

[PDF](<https://arxiv.org/pdf/1702.06376.pdf>)