SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.08131 · ICCV · 2023

A Simple Framework for Open-Vocabulary Segmentation and Detection

Chunyuan Li, Lei Zhang, Hao Zhang, Jianwei Yang, Shilong Liu, Feng Li, Xueyan Zou, Coco Panoptic, Cityscapes Panoptic

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Top row: visualizations of OpenSeeD for open-vocabulary instance segmentation and detection, panoptic and semantic segmentation, instance segmentation in the wild, and conditioned segmentation given referring box location and concept. Bottom row: Our OpenSeeD model outperforms previous state-of-the-art methods (listed below each gray bar) on eight benchmarks in zero-shot and task-specific transfer settings.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.08131")
get_code_for_paper("2303.08131")
have("2303.08131")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2303.08131.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2303.08131.svg)](https://syntology.ai/paper/2303.08131)

Connect an agent — have() is free.