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

computer-vision-2

Open Vocabulary Panoptic Segmentation

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in open-vocabulary-panoptic-segmentation-2

Trend

Dataset

Best Model

Actions

ADE20K

Libraries

Use these libraries to find open-vocabulary-panoptic-segmentation-2 models and implementations

Datasets

ADE20K

Subtasks

No subtasks available.

Most implemented papers

Panoptic Vision-Language Feature Fields

Haoran Chen, Kenneth Blomqvist, Francesco Milano, R. Siegwart•Sun Sep 10 2023

This letter proposes the first algorithm for open-vocabulary panoptic segmentation in 3D scenes, which achieves panoptic segmentation performance similar to the state-of-the-art closed-set 3D systems on the HyperSim, ScanNet and Replica dataset and additionally outperforms current 3D open-vocabulary systems in terms of semantic segmentation.

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Extract Free Dense Labels from CLIP

Chen Change Loy, Bo Dai, Chong Zhou•Wed Dec 01 2021

The finding suggests that MaskCLIP can serve as a new reliable source of supervision for dense prediction tasks to achieve annotation-free segmentation in pixel-level dense prediction, specifically in semantic segmentation.

661 0

Paper Graph

Open-Vocabulary Universal Image Segmentation with MaskCLIP

Z. Tu, Zheng Ding•Wed Aug 17 2022

The developed MaskCLIP is an encoder-only module that seamlessly integrates mask tokens with a pre-trained ViT CLIP model for semantic/instance segmentation and class prediction that avoids the time-consuming student-teacher training process.

130 0

Paper Graph

Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models

Arash Vahdat, Wonmin Byeon, Jiarui Xu, Sifei Liu, Shalini De Mello, Xiaolong Wang•Tue Mar 07 2023

ODISE is presented, which unifies pre-trained text-image diffusion and discriminative models to perform open-vocabulary panoptic segmentation and outperforms the previous state of the art by significant margins on both open- VocabularyPanoptic and semantic segmentation tasks.

409 0

Paper Graph

Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

Xiaohui Shen, Liang-Chieh Chen, Ju He, Qihang Yu, Xueqing Deng•Thu Aug 03 2023

This work proposes to build everything into a single-stage framework using a shared Frozen Convolutional CLIP backbone, which not only significantly simplifies the current two-stage pipeline, but also remarkably yields a better accuracy-cost trade-off.

211 0

Paper Graph

CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

Lumin Xu, Wenwei Zhang, Sheng Jin, Chen Change Loy, Xiangtai Li, Size Wu, Wentao Liu•Sun Oct 01 2023

An in-depth analysis of the region-language alignment in CLIP models is embarked on, which proposes an approach named CLIPSelf, which adapts the image-level recognition ability of CLIP ViT to local image regions without needing any region-text pairs.

108 0

Paper Graph

PosSAM: Panoptic Open-vocabulary Segment Anything

F. Porikli, Munawar Hayat, Debasmit Das, VS Vibashan, Shubhankar Borse, Hyojin Park, Vishal M. Patel•Wed Mar 13 2024

An open-vocabulary panoptic segmentation model that effectively unifies the strengths of the Segment Anything Model with the vision-language CLIP model in an end-to-end framework and proposes a novel Local Discriminative Pooling (LDP) module leveraging class-agnostic SAM and class-aware CLIP features for unbiased open-vocabulary classification.

9 0

Paper Graph

Adding a benchmark result helps the community track progress.

Open Vocabulary Panoptic Segmentation | State-of-the-Art