# NeurIPS 2019 Disentanglement Challenge: Improved Disentanglement through Aggregated Convolutional Feature Maps

Source: [NeurIPS 2019 Disentanglement Challenge: Improved Disentanglement through Aggregated Convolutional Feature Maps](<https://www.sota2.com/research/paper/68fa67181e209131cea1417f>)

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

Data updated: 2025-10-27T06:01:46.445Z

Authors: Maximilian Seitzer

Published: 2020-02-23T22:35:59.000Z

## Abstract

This report to our stage 1 submission to the NeurIPS 2019 disentanglement challenge presents a simple image preprocessing method for training VAEs leading to improved disentanglement compared to directly using the images. In particular, we propose to use regionally aggregated feature maps extracted from CNNs pretrained on ImageNet. Our method achieved the 2nd place in stage 1 of the challenge. Code is available at https://github.com/mseitzer/neurips2019-disentanglement-challenge.

## 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/2002.10003>)

[PDF](<https://arxiv.org/pdf/2002.10003.pdf>)