Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision-10

Universal Segmentation

3260 papers • 126 benchmarks • 313 datasets

Universal segmentation is a challenging computer vision task that aims to segment images into semantic regions, regardless of the task or the domain. It requires the model to learn a wide range of visual concepts and to be able to generalize to new tasks and domains.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in universal-segmentation-10

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find universal-segmentation-10 models and implementations

huggingface/transformers

2 papers 128,631

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Masked-attention Mask Transformer for Universal Image Segmentation

A. Schwing, Ishan Misra, Alexander Kirillov, Rohit Girdhar, Bowen Cheng•Wed Dec 01 2021

Mask2Former is presented, a new archi-tecture capable of addressing any image segmentation task (panoptic, instance or semantic), and sets a new state-of-the-art for panoptic segmentation, instance segmentation and semantic segmentation.

3400

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

OneFormer: One Transformer to Rule Universal Image Segmentation

Humphrey Shi, Jitesh Jain, Jiacheng Li, M. Chiu, Ali Hassani, Nikita Orlov•Wed Nov 09 2022

This work proposes OneFormer, a universal image segmentation framework that unifies segmentation with a multi-task train-once design that outperforms specialized Mask2Former models across all three segmentation tasks on ADE20k, Cityscapes, and COCO.

499 0

Training a universal instance segmentation network for live cell images of various cell types and imaging modalities

J. Allebach, Tianqi Guo, Yin Wang, Luis Solorio•Wed Jul 27 2022

This work modified the traditional binary training targets to include three classes for direct instance segmentation, and found that segmentation performance can benefit from group normalization layer and Atrous Spatial Pyramid Pooling module, thanks to their more reliable statistics estimation and improved semantic understanding.

3 0

UniSeg: A Prompt-driven Universal Segmentation Model as well as A Strong Representation Learner

Jianpeng Zhang, Yutong Xie, Yiwen Ye, Ziyang Chen, Yong Xia•Thu Apr 06 2023

A prompt-driven Universal Segmentation model (UniSeg) for multi-task medical image segmentation using diverse modalities and domains is proposed, which outperforms other universal models and single-task models on 11 upstream tasks and beats other pre-trained models on two downstream datasets.

69 0

Segment Everything Everywhere All at Once

Jianfeng Gao, Jianwei Yang, Linjie Li, Yong Jae Lee, Xueyan Zou, Hao Zhang, Feng Li•Wed Apr 12 2023

This work proposes a novel decoding mechanism that enables diverse prompting for all types of segmentation tasks, aiming at a universal segmentation interface that behaves like large language models (LLMs).

701 0

CLUSTSEG: Clustering for Universal Segmentation

Wenguan Wang, J. Liang, Tianfei Zhou, Dongfang Liu•Tue May 02 2023

These innovations closely link CLUSTSEG to EM clustering and make it a transparent and powerful framework that yields superior results across the above segmentation tasks.

77 0

Hierarchical Open-vocabulary Universal Image Segmentation

Trevor Darrell, K. Kozuka, Xudong Wang, Shufang Li, Konstantinos Kallidromitis, Yu Kato•Sun Jul 02 2023

The resulting model, named HIPIE, tackles HIerarchical, oPen-vocabulary, and unIvErsal segmentation tasks within a unified framework and achieves the state-of-the-art results at various levels of image comprehension.

63 0

Universal Segmentation at Arbitrary Granularity with Language Instruction

Yujiu Yang, Yong Liu, Cairong Zhang, Yitong Wang, Jiahao Wang, Yansong Tang•Sun Dec 03 2023

Unified segmentation model UniLSeg is presented, a universal segmentation model that can perform segmentation at any semantic level with the guidance of language instructions, surpassing both specialist and unified segmentation models.

30 0

Unsupervised Universal Image Segmentation

Roei Herzig, Dantong Niu, Xudong Wang, Xinyang Han, Long Lian, Trevor Darrell•Wed Dec 27 2023

An Unsupervised Universal Segmentation model (U2Seg) adept at performing various image segmentation tasks-instance, semantic and panoptic-using a novel uni-fied framework is proposed, which sets up a new baseline for unsupervised panoptic segmentation, which has not been previously explored.

38 0

OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding

Shengqiong Wu, Chen Change Loy, Haobo Yuan, Tao Zhang, Xiangtai Li, Hao Fei, Shunping Ji, Shuicheng Yan•Wed Jun 26 2024

This paper uses a universal segmentation method as the visual encoder, integrating image information, perception priors, and visual prompts into visual tokens provided to the LLM, and proposes perception prior embedding to better integrate perception priors with image features.

124 0

Adding a benchmark result helps the community track progress.

Universal Segmentation | State-of-the-Art