CVAILGJun 22, 2022

The ArtBench Dataset: Benchmarking Generative Models with Artworks

arXiv:2206.11404v173 citationsh-index: 97Has Code
Originality Synthesis-oriented
AI Analysis

This provides a standardized benchmark for researchers in generative AI to compare artwork generation models, though it is incremental as it builds on existing dataset creation efforts.

They introduced ArtBench-10, a class-balanced, high-quality dataset of 60,000 artwork images across 10 styles, to benchmark generative models, and conducted experiments showing its utility for standardized evaluation.

We introduce ArtBench-10, the first class-balanced, high-quality, cleanly annotated, and standardized dataset for benchmarking artwork generation. It comprises 60,000 images of artwork from 10 distinctive artistic styles, with 5,000 training images and 1,000 testing images per style. ArtBench-10 has several advantages over previous artwork datasets. Firstly, it is class-balanced while most previous artwork datasets suffer from the long tail class distributions. Secondly, the images are of high quality with clean annotations. Thirdly, ArtBench-10 is created with standardized data collection, annotation, filtering, and preprocessing procedures. We provide three versions of the dataset with different resolutions ($32\times32$, $256\times256$, and original image size), formatted in a way that is easy to be incorporated by popular machine learning frameworks. We also conduct extensive benchmarking experiments using representative image synthesis models with ArtBench-10 and present in-depth analysis. The dataset is available at https://github.com/liaopeiyuan/artbench under a Fair Use license.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes