Universal Segmentation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

No dataset record in the archive lists this task.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

25 shown of 25 papers with code (32 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Masked-attention Mask Transformer for Universal Image Segmentation
  2 Dec 2021 7 repositories listed Syntology ran 2 of 8 samples · 6 unverified
  While only the semantics of each task differ, current research focuses on designing specialized architectures for each task.
• OneFormer: One Transformer to Rule Universal Image Segmentation
  10 Nov 2022 4 repositories listed Syntology ran 0 of 5 samples · 5 unverified
  However, such panoptic architectures do not truly unify image segmentation because they need to be trained individually on the semantic, instance, or panoptic segmentation to achieve the best performance.
• Rethinking the Evaluation of Visible and Infrared Image Fusion
  9 Oct 2024 3 repositories listed
  Visible and Infrared Image Fusion (VIF) has garnered significant interest across a wide range of high-level vision tasks, such as object detection and semantic segmentation.
• Segment Everything Everywhere All at Once
  13 Apr 2023 3 repositories listed
  In SEEM, we propose 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).
• Unsupervised Universal Image Segmentation
  28 Dec 2023 2 repositories listed Syntology ran 13 of 15 samples · 2 unverified
  Several unsupervised image segmentation approaches have been proposed which eliminate the need for dense manually-annotated segmentation masks; current models separately handle either semantic segmentation (e.
• One Model to Rule them All: Towards Universal Segmentation for Medical Images with Text Prompts
  28 Dec 2023 2 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 3 pointer-only (licence)
  Our main contributions are three folds: (i) for dataset construction, we construct the first multi-modal knowledge tree on human anatomy, including 6502 anatomical terminologies; Then, we build up the largest and most…
• Universal Segmentation at Arbitrary Granularity with Language Instruction
  4 Dec 2023 2 repositories listed Syntology ran 13 of 16 samples · 3 unverified
  This paper aims to achieve universal segmentation of arbitrary semantic level.
• The Missing Point in Vision Transformers for Universal Image Segmentation
  26 May 2025 1 repository listed
  Image segmentation remains a challenging task in computer vision, demanding robust mask generation and precise classification.
• SemiSAM+: Rethinking Semi-Supervised Medical Image Segmentation in the Era of Foundation Models
  28 Feb 2025 1 repository listed
  SemiSAM+ consists of one or multiple promptable foundation models as generalist models, and a trainable task-specific segmentation model as specialist model.
• SegAnyPET: Universal Promptable Segmentation from Positron Emission Tomography Images
  20 Feb 2025 1 repository listed
  Positron Emission Tomography (PET) imaging plays a crucial role in modern medical diagnostics by revealing the metabolic processes within a patient's body, which is essential for quantification of therapy response and…
• MedicoSAM: Towards foundation models for medical image segmentation
  20 Jan 2025 1 repository listed
  We evaluate the finetuned models on a wide range of interactive and (automatic) semantic segmentation tasks.
• FOCUS: Towards Universal Foreground Segmentation
  9 Jan 2025 1 repository listed
  Foreground segmentation is a fundamental task in computer vision, encompassing various subdivision tasks.
• VOILA: Complexity-Aware Universal Segmentation of CT images by Voxel Interacting with Language
  7 Jan 2025 1 repository listed
  Satisfactory progress has been achieved recently in universal segmentation of CT images.
• HyperSeg: Hybrid Segmentation Assistant with Fine-grained Visual Perceiver
  1 Jan 2025 1 repository listed
  This paper aims to address universal segmentation for image and video perception with the strong reasoning ability empowered by Visual Large Language Models (VLLMs).
• InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models
  18 Dec 2024 1 repository listed Syntology ran 6 of 14 samples · 8 unverified
  Boosted by Multi-modal Large Language Models (MLLMs), text-guided universal segmentation models for the image and video domains have made rapid progress recently.
• HyperSeg: Towards Universal Visual Segmentation with Large Language Model
  26 Nov 2024 1 repository listed Syntology ran 7 of 17 samples · 10 unverified
  This paper aims to address universal segmentation for image and video perception with the strong reasoning ability empowered by Visual Large Language Models (VLLMs).
• Large Language Model with Region-guided Referring and Grounding for CT Report Generation
  23 Nov 2024 1 repository listed
  It leverages the recognition of referring regions to guide the generation of region-specific reports, enhancing the model's referring and grounding capabilities while also improving the report's interpretability.
• MedUniSeg: 2D and 3D Medical Image Segmentation via a Prompt-driven Universal Model
  8 Oct 2024 1 repository listed
  In this paper, we introduce MedUniSeg, a prompt-driven universal segmentation model designed for 2D and 3D multi-task segmentation across diverse modalities and domains.
• OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding
  27 Jun 2024 1 repository listed Syntology ran 2 of 4 samples · 2 unverified · 4 pointer-only (licence)
  Current universal segmentation methods demonstrate strong capabilities in pixel-level image and video understanding.
• RadGenome-Chest CT: A Grounded Vision-Language Dataset for Chest CT Analysis
  25 Apr 2024 1 repository listed
  We believe that RadGenome-Chest CT can significantly advance the development of multimodal medical foundation models, by training to generate texts based on given segmentation regions, which is unattainable with…
• Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation
  23 Apr 2024 1 repository listed Syntology ran 2 of 7 samples · 5 unverified · 7 pointer-only (licence)
  A powerful architecture for universal segmentation relies on transformers that encode multi-scale image features and decode object queries into mask predictions.
• Hierarchical Open-vocabulary Universal Image Segmentation
  3 Jul 2023 1 repository listed Syntology ran 2 of 4 samples · 2 unverified
  Open-vocabulary image segmentation aims to partition an image into semantic regions according to arbitrary text descriptions.
• CLUSTSEG: Clustering for Universal Segmentation
  3 May 2023 1 repository listed
  We present CLUSTSEG, a general, transformer-based framework that tackles different image segmentation tasks (i.
• UniSeg: A Prompt-driven Universal Segmentation Model as well as A Strong Representation Learner
  7 Apr 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Moreover, UniSeg also beats other pre-trained models on two downstream datasets, providing the community with a high-quality pre-trained model for 3D medical image segmentation.
• Training a universal instance segmentation network for live cell images of various cell types and imaging modalities
  28 Jul 2022 1 repository listed
  We share our recent findings in an attempt to train a universal segmentation network for various cell types and imaging modalities.

Syntology lines on 11 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.