# Universal Segmentation at Arbitrary Granularity with Language Instruction

arXiv: https://arxiv.org/abs/2312.01623 · HTML: https://mlsanity.com/paper/2312.01623/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 62 of its 84 references that are in the map.
- First posted on arXiv 4 Dec 2023.

## Builds on (most cited first, 30 of 62)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation](https://mlsanity.com/paper/1611.06612/) (2016)
- [MAttNet: Modular Attention Network for Referring Expression Comprehension](https://mlsanity.com/paper/1801.08186/) (2018)
- [CRIS: CLIP-Driven Referring Image Segmentation](https://mlsanity.com/paper/2111.15174/) (2021)
- [LAVT: Language-Aware Vision Transformer for Referring Image Segmentation](https://mlsanity.com/paper/2112.02244/) (2021)
- [Images Speak in Images: A Generalist Painter for In-Context Visual Learning](https://mlsanity.com/paper/2212.02499/) (2022)
- [Recognize Anything: A Strong Image Tagging Model](https://mlsanity.com/paper/2306.03514/) (2023)
- [Cross-Modal Self-Attention Network for Referring Image Segmentation](https://mlsanity.com/paper/1904.04745/) (2019)
- [Segmentation from Natural Language Expressions](https://mlsanity.com/paper/1603.06180/) (2016)

## Built on by (most cited first, 29 of 29)

- [Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams](https://mlsanity.com/paper/2406.08085/) (2024)
- [UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning](https://mlsanity.com/paper/2505.14231/) (2025)
- [Flash-VStream: Efficient Real-Time Understanding for Long Video Streams](https://mlsanity.com/paper/2506.23825/) (2025)
- [EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model](https://mlsanity.com/paper/2406.20076/) (2024)
- [Open-Vocabulary Segmentation with Semantic-Assisted Calibration](https://mlsanity.com/paper/2312.04089/) (2023)
- [KV-Edit: Training-Free Image Editing for Precise Background Preservation](https://mlsanity.com/paper/2502.17363/) (2025)
- [Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation](https://mlsanity.com/paper/2411.15869/) (2024)
- [HyperSeg: Towards Universal Visual Segmentation with Large Language Model](https://mlsanity.com/paper/2411.17606/) (2024)
- [IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis](https://mlsanity.com/paper/2503.00936/) (2025)
- [SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes](https://mlsanity.com/paper/2506.01558/) (2025)
- [Hierarchical Memory for Long Video QA](https://mlsanity.com/paper/2407.00603/) (2024)
- [DreamLight: Towards Harmonious and Consistent Image Relighting](https://mlsanity.com/paper/2506.14549/) (2025)
- [VG-Refiner: Towards Tool-Refined Referring Grounded Reasoning via Agentic Reinforcement Learning](https://mlsanity.com/paper/2512.06373/) (2025)
- [STPNet: Scale-aware Text Prompt Network for Medical Image Segmentation](https://mlsanity.com/paper/2504.01561/) (2025)
- [Deep Instruction Tuning for Segment Anything Model](https://mlsanity.com/paper/2404.00650/) (2024)
- [Stepping Out of Similar Semantic Space for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2506.16058/) (2025)
- [Evolving, Not Training: Zero-Shot Reasoning Segmentation via Evolutionary Prompting](https://mlsanity.com/paper/2512.24702/) (2025)
- [TalkPhoto: A Versatile Training-Free Conversational Assistant for Intelligent Image Editing](https://mlsanity.com/paper/2601.01915/) (2026)
- [Conversational Image Segmentation: Grounding Abstract Concepts with Scalable Supervision](https://mlsanity.com/paper/2602.13195/) (2026)
- [Data-Centric AI Governance: Addressing the Limitations of Model-Focused Policies](https://mlsanity.com/paper/2409.17216/) (2024)
- [Diffusion Instruction Tuning](https://mlsanity.com/paper/2502.06814/) (2025)
- [Boosting Medical Visual Understanding From Multi-Granular Language Learning](https://mlsanity.com/paper/2511.15943/) (2025)
- [SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction](https://mlsanity.com/paper/2605.20110/) (2026)
- [Evidential learning driven Breast Tumor Segmentation with Stage-divided Vision-Language Interaction](https://mlsanity.com/paper/2603.11206/) (2026)
- [Tarot-SAM3: Training-free SAM3 for Any Referring Expression Segmentation](https://mlsanity.com/paper/2604.07916/) (2026)
- [Vision Harnessing Agent for Open Ad-hoc Segmentation](https://mlsanity.com/paper/2605.19410/) (2026)
- [Fully Aligned Network for Referring Image Segmentation](https://mlsanity.com/paper/2409.19569/) (2024)
- [Spatio-Semantic Expert Routing Architecture with Mixture-of-Experts for Referring Image Segmentation](https://mlsanity.com/paper/2603.12538/) (2026)
- [AgentRVOS for MeViS-Text Track of 5th PVUW Challenge: 3rd Method](https://mlsanity.com/paper/2604.22836/) (2026)

## Abstract (arXiv)

This paper aims to achieve universal segmentation of arbitrary semantic level. Despite significant progress in recent years, specialist segmentation approaches are limited to specific tasks and data distribution. Retraining a new model for adaptation to new scenarios or settings takes expensive computation and time cost, which raises the demand for versatile and universal segmentation model that can cater to various granularity. Although some attempts have been made for unifying different segmentation tasks or generalization to various scenarios, limitations in the definition of paradigms and input-output spaces make it difficult for them to achieve accurate understanding of content at arbitrary granularity. To this end, we present UniLSeg, a universal segmentation model that can perform segmentation at any semantic level with the guidance of language instructions. For training UniLSeg, we reorganize a group of tasks from original diverse distributions into a unified data format, where images with texts describing segmentation targets as input and corresponding masks are output. Combined with a automatic annotation engine for utilizing numerous unlabeled data, UniLSeg achieves excellent performance on various tasks and settings, surpassing both specialist and unified segmentation models.