# Open Vocabulary Scene Parsing

Source: [Open Vocabulary Scene Parsing](<https://www.sota2.com/research/paper/68fa63371e209131ce9fd7a4>)

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

Data updated: 2025-10-25T20:36:15.201Z

Authors: Hang Zhao, Xavier Puig, Bolei Zhou, Sanja Fidler, Antonio Torralba

Published: 2017-03-26T05:44:56.000Z

## Abstract

Recognizing arbitrary objects in the wild has been a challenging problem due to the limitations of existing classification models and datasets. In this paper, we propose a new task that aims at parsing scenes with a large and open vocabulary, and several evaluation metrics are explored for this problem. Our proposed approach to this problem is a joint image pixel and word concept embeddings framework, where word concepts are connected by semantic relations. We validate the open vocabulary prediction ability of our framework on ADE20K dataset which covers a wide variety of scenes and objects. We further explore the trained joint embedding space to show its interpretability.

## 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.

- [Semantic Segmentation on ADE20K (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-val.md>): Semantic segmentation; ADE20K (val); mIoU: 31.52.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1703.08769>)

[PDF](<https://arxiv.org/pdf/1703.08769.pdf>)