# ChoiceNet: CNN learning through choice of multiple feature map representations

Source: [ChoiceNet: CNN learning through choice of multiple feature map representations](<https://www.sota2.com/research/paper/68fa66421e209131cea0f437>)

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

Data updated: 2025-10-25T21:46:30.691Z

Authors: Farshid Rayhan, Aphrodite Galata, Timothy F. Cootes

Published: 2019-04-20T17:37:46.000Z

## Abstract

We introduce a new architecture called ChoiceNet where each layer of the network is highly connected with skip connections and channelwise concatenations. This enables the network to alleviate the problem of vanishing gradients, reduces the number of parameters without sacrificing performance, and encourages feature reuse. We evaluate our proposed architecture on three benchmark datasets for object recognition tasks (ImageNet, CIFAR- 10, CIFAR-100, SVHN) and on a semantic segmentation dataset (CamVid).

## 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/1904.09472>)

[PDF](<https://arxiv.org/pdf/1904.09472.pdf>)