# Hierarchical Open-vocabulary Universal Image Segmentation

arXiv: https://arxiv.org/abs/2307.00764 · HTML: https://mlsanity.com/paper/2307.00764/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 71 references that are in the map.
- First posted on arXiv 3 Jul 2023.

## Builds on (most cited first, 30 of 54)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [Segment Everything Everywhere All at Once](https://mlsanity.com/paper/2304.06718/) (2023)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://mlsanity.com/paper/2202.11094/) (2022)
- [DN-DETR: Accelerate DETR Training by Introducing Query DeNoising](https://mlsanity.com/paper/2203.01305/) (2022)
- [Scaling Open-Vocabulary Image Segmentation with Image-Level Labels](https://mlsanity.com/paper/2112.12143/) (2021)
- [MAttNet: Modular Attention Network for Referring Expression Comprehension](https://mlsanity.com/paper/1801.08186/) (2018)

## Built on by (most cited first, 30 of 54)

- [Osprey: Pixel Understanding with Visual Instruction Tuning](https://mlsanity.com/paper/2312.10032/) (2023)
- [ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2408.04883/) (2024)
- [Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want](https://mlsanity.com/paper/2403.20271/) (2024)
- [SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2311.15537/) (2023)
- [OMG-Seg: Is One Model Good Enough For All Segmentation?](https://mlsanity.com/paper/2401.10229/) (2024)
- [A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future](https://mlsanity.com/paper/2307.09220/) (2023)
- [Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation](https://mlsanity.com/paper/2310.03923/) (2023)
- [Toward Visual Grounding: A Survey](https://mlsanity.com/paper/2412.20206/) (2024)
- [Search3D: Hierarchical Open-Vocabulary 3D Segmentation](https://mlsanity.com/paper/2409.18431/) (2024)
- [OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling](https://mlsanity.com/paper/2410.08021/) (2024)
- [Multi-Space Alignments Towards Universal LiDAR Segmentation](https://mlsanity.com/paper/2405.01538/) (2024)
- [SegLLM: Multi-round Reasoning Segmentation](https://mlsanity.com/paper/2410.18923/) (2024)
- [LLM-driven Multimodal Target Volume Contouring in Radiation Oncology](https://mlsanity.com/paper/2311.01908/) (2023)
- [Open Panoramic Segmentation](https://mlsanity.com/paper/2407.02685/) (2024)
- [Visually Consistent Hierarchical Image Classification](https://mlsanity.com/paper/2406.11608/) (2024)
- [Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2403.10001/) (2024)
- [PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects](https://mlsanity.com/paper/2407.16696/) (2024)
- [DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency](https://mlsanity.com/paper/2504.12080/) (2025)
- [OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts](https://mlsanity.com/paper/2507.05427/) (2025)
- [Intra- and Cross-Scale Feature Interaction Network for Referring Remote Sensing Image Segmentation](https://mlsanity.com/paper/2506.03583/) (2025)
- [UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes](https://mlsanity.com/paper/2511.23332/) (2025)
- [Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models](https://mlsanity.com/paper/2403.07733/) (2024)
- [Enhancing Domain Adaptation through Prompt Gradient Alignment](https://mlsanity.com/paper/2406.09353/) (2024)
- [DPSeg: Dual-Prompt Cost Volume Learning for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2505.11676/) (2025)
- [Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding](https://mlsanity.com/paper/2404.08590/) (2024)
- [Unified Open-World Segmentation with Multi-Modal Prompts](https://mlsanity.com/paper/2510.10524/) (2025)
- [Better, Stronger, Faster: Tackling the Trilemma in MLLM-based Segmentation with Simultaneous Textual Mask Prediction](https://mlsanity.com/paper/2512.00395/) (2025)
- [OVFoodSeg: Elevating Open-Vocabulary Food Image Segmentation via Image-Informed Textual Representation](https://mlsanity.com/paper/2404.01409/) (2024)
- [SPIN: Hierarchical Segmentation with Subpart Granularity in Natural Images](https://mlsanity.com/paper/2407.09686/) (2024)
- [MR-GDINO: Efficient Open-World Continual Object Detection](https://mlsanity.com/paper/2412.15979/) (2024)

## Abstract (arXiv)

Open-vocabulary image segmentation aims to partition an image into semantic regions according to arbitrary text descriptions. However, complex visual scenes can be naturally decomposed into simpler parts and abstracted at multiple levels of granularity, introducing inherent segmentation ambiguity. Unlike existing methods that typically sidestep this ambiguity and treat it as an external factor, our approach actively incorporates a hierarchical representation encompassing different semantic-levels into the learning process. We propose a decoupled text-image fusion mechanism and representation learning modules for both "things" and "stuff". Additionally, we systematically examine the differences that exist in the textual and visual features between these types of categories. Our resulting model, named HIPIE, tackles HIerarchical, oPen-vocabulary, and unIvErsal segmentation tasks within a unified framework. Benchmarked on over 40 datasets, e.g., ADE20K, COCO, Pascal-VOC Part, RefCOCO/RefCOCOg, ODinW and SeginW, HIPIE achieves the state-of-the-art results at various levels of image comprehension, including semantic-level (e.g., semantic segmentation), instance-level (e.g., panoptic/referring segmentation and object detection), as well as part-level (e.g., part/subpart segmentation) tasks. Our code is released at https://github.com/berkeley-hipie/HIPIE.