# SEA: Evaluating Sketch Abstraction Efficiency via Element-level Commonsense Visual Question Answering

Source: [SEA: Evaluating Sketch Abstraction Efficiency via Element-level Commonsense Visual Question Answering](<https://www.sota2.com/research/paper/69cb55790636e5bf4afca37d>)

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

Data updated: 2026-04-01T05:00:12.613Z

Authors: Jiho Park, Sieun Choi, Jaeyoon Seo, Minho Sohn, Yeana Kim, Jihie Kim

Published: 2026-03-30T12:30:51.000Z

## Abstract

A sketch is a distilled form of visual abstraction that conveys core concepts through simplified yet purposeful strokes while omitting extraneous detail. Despite its expressive power, quantifying the efficiency of semantic abstraction in sketches remains challenging. Existing evaluation methods that rely on reference images, low-level visual features, or recognition accuracy do not capture abstraction, the defining property of sketches. To address these limitations, we introduce SEA (Sketch Evaluation metric for Abstraction efficiency), a reference-free metric that assesses how economically a sketch represents class-defining visual elements while preserving semantic recognizability. These elements are derived per class from commonsense knowledge about features typically depicted in sketches. SEA leverages a visual question answering model to determine the presence of each element and returns a quantitative score that reflects semantic retention under visual economy. To support this metric, we present CommonSketch, the first semantically annotated sketch dataset, comprising 23,100 human-drawn sketches across 300 classes, each paired with a caption and element-level annotations. Experiments show that SEA aligns closely with human judgments and reliably discriminates levels of abstraction efficiency, while CommonSketch serves as a benchmark providing systematic evaluation of element-level sketch understanding across various vision-language models.

## 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.

- [element-level commonsense VQA on CommonSketch](<https://www.sota2.com/research/sota/element-level-commonsense-vqa-on-commonsketch.md>): element-level commonsense VQA; CommonSketch; Precision: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.28363>)

[PDF](<https://arxiv.org/pdf/2603.28363.pdf>)