TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Hierarchical Open-vocabulary Universal Image Segmentation

Hierarchical Open-vocabulary Universal Image Segmentation

Xudong Wang, Shufan Li, Konstantinos Kallidromitis, Yusuke Kato, Kazuki Kozuka, Trevor Darrell

2023-07-03NeurIPS 2023 11Panoptic SegmentationRepresentation LearningImage ComprehensionZero Shot SegmentationReferring Expression SegmentationSegmentationSemantic Segmentationobject-detectionObject DetectionImage Segmentation
PaperPDFCode(official)

Abstract

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.

Results

TaskDatasetMetricValueModel
Semantic SegmentationCOCO minivalPQ58.1HIPIE (ViT-H, single-scale)
Semantic SegmentationCOCO minivalmIoU66.8HIPIE (ViT-H, single-scale)
Instance SegmentationRefCoCo valOverall IoU82.8HIPIE
Instance SegmentationRefCOCO+ valOverall IoU73.9HIPIE
Zero Shot SegmentationSegmentation in the WildMean AP41.6HIPIE
Referring Expression SegmentationRefCoCo valOverall IoU82.8HIPIE
Referring Expression SegmentationRefCOCO+ valOverall IoU73.9HIPIE
2D Semantic SegmentationPascal Panoptic PartsmIoUPartS63.8HIPIE (ViT-H)
2D Semantic SegmentationPascal Panoptic PartsmIoUPartS57.2HIPIE (ResNet-50)
10-shot image generationCOCO minivalPQ58.1HIPIE (ViT-H, single-scale)
10-shot image generationCOCO minivalmIoU66.8HIPIE (ViT-H, single-scale)
Panoptic SegmentationCOCO minivalPQ58.1HIPIE (ViT-H, single-scale)
Panoptic SegmentationCOCO minivalmIoU66.8HIPIE (ViT-H, single-scale)
Image SegmentationPascal Panoptic PartsmIoUPartS63.8HIPIE (ViT-H)
Image SegmentationPascal Panoptic PartsmIoUPartS57.2HIPIE (ResNet-50)

Related Papers

SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction2025-07-21Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper2025-07-20Spectral Bellman Method: Unifying Representation and Exploration in RL2025-07-17Boosting Team Modeling through Tempo-Relational Representation Learning2025-07-17Deep Learning-Based Fetal Lung Segmentation from Diffusion-weighted MRI Images and Lung Maturity Evaluation for Fetal Growth Restriction2025-07-17DiffOSeg: Omni Medical Image Segmentation via Multi-Expert Collaboration Diffusion Model2025-07-17From Variability To Accuracy: Conditional Bernoulli Diffusion Models with Consensus-Driven Correction for Thin Structure Segmentation2025-07-17Unleashing Vision Foundation Models for Coronary Artery Segmentation: Parallel ViT-CNN Encoding and Variational Fusion2025-07-17