# Bias in Automated Image Colorization: Metrics and Error Types

Source: [Bias in Automated Image Colorization: Metrics and Error Types](<https://www.sota2.com/research/paper/68fa6bda1e209131cea309e3>)

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

Data updated: 2025-10-25T23:58:04.948Z

Authors: Frank Stapel, Floris Weers, Doina Bucur

Published: 2022-02-16T15:34:09.000Z

## Abstract

We measure the color shifts present in colorized images from the ADE20K dataset, when colorized by the automatic GAN-based DeOldify model. We introduce fine-grained local and regional bias measurements between the original and the colorized images, and observe many colorization effects. We confirm a general desaturation effect, and also provide novel observations: a shift towards the training average, a pervasive blue shift, different color shifts among image categories, and a manual categorization of colorization errors in three classes.

## 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/2202.08143>)

[PDF](<https://arxiv.org/pdf/2202.08143.pdf>)