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/Part-aware Prototype Network for Few-shot Semantic Segment...

Part-aware Prototype Network for Few-shot Semantic Segmentation

Yongfei Liu, Xiangyi Zhang, Songyang Zhang, Xuming He

2020-07-13ECCV 2020 8Semi-Supervised Semantic SegmentationSegmentationFew-Shot Semantic SegmentationSemantic Segmentation
PaperPDFCode(official)Code

Abstract

Few-shot semantic segmentation aims to learn to segment new object classes with only a few annotated examples, which has a wide range of real-world applications. Most existing methods either focus on the restrictive setting of one-way few-shot segmentation or suffer from incomplete coverage of object regions. In this paper, we propose a novel few-shot semantic segmentation framework based on the prototype representation. Our key idea is to decompose the holistic class representation into a set of part-aware prototypes, capable of capturing diverse and fine-grained object features. In addition, we propose to leverage unlabeled data to enrich our part-aware prototypes, resulting in better modeling of intra-class variations of semantic objects. We develop a novel graph neural network model to generate and enhance the proposed part-aware prototypes based on labeled and unlabeled images. Extensive experimental evaluations on two benchmarks show that our method outperforms the prior art with a sizable margin.

Results

TaskDatasetMetricValueModel
Few-Shot LearningCOCO-20i (5-shot)Mean IoU38.5PPNet (ResNet-50)
Few-Shot LearningCOCO-20i (5-shot)learnable parameters (million)31.5PPNet (ResNet-50)
Few-Shot LearningCOCO-20i (2-way 1-shot)mIoU20.4PPNet (ResNet-50)
Few-Shot LearningPASCAL-5i (1-Shot)Mean IoU51.5PPNet (ResNet-50)
Few-Shot LearningPASCAL-5i (1-Shot)learnable parameters (million)31.5PPNet (ResNet-50)
Few-Shot LearningCOCO-20i (1-shot)Mean IoU29PPNet (ResNet-50)
Few-Shot LearningCOCO-20i (1-shot)learnable parameters (million)31.5PPNet (ResNet-50)
Few-Shot LearningPascal5imeanIOU55.16PPNet
Few-Shot LearningPASCAL-5i (5-Shot)Mean IoU62PPNet (ResNet-50)
Few-Shot LearningPASCAL-5i (5-Shot)learnable parameters (million)31.5PPNet (ResNet-50)
Few-Shot Semantic SegmentationCOCO-20i (5-shot)Mean IoU38.5PPNet (ResNet-50)
Few-Shot Semantic SegmentationCOCO-20i (5-shot)learnable parameters (million)31.5PPNet (ResNet-50)
Few-Shot Semantic SegmentationCOCO-20i (2-way 1-shot)mIoU20.4PPNet (ResNet-50)
Few-Shot Semantic SegmentationPASCAL-5i (1-Shot)Mean IoU51.5PPNet (ResNet-50)
Few-Shot Semantic SegmentationPASCAL-5i (1-Shot)learnable parameters (million)31.5PPNet (ResNet-50)
Few-Shot Semantic SegmentationCOCO-20i (1-shot)Mean IoU29PPNet (ResNet-50)
Few-Shot Semantic SegmentationCOCO-20i (1-shot)learnable parameters (million)31.5PPNet (ResNet-50)
Few-Shot Semantic SegmentationPascal5imeanIOU55.16PPNet
Few-Shot Semantic SegmentationPASCAL-5i (5-Shot)Mean IoU62PPNet (ResNet-50)
Few-Shot Semantic SegmentationPASCAL-5i (5-Shot)learnable parameters (million)31.5PPNet (ResNet-50)
Meta-LearningCOCO-20i (5-shot)Mean IoU38.5PPNet (ResNet-50)
Meta-LearningCOCO-20i (5-shot)learnable parameters (million)31.5PPNet (ResNet-50)
Meta-LearningCOCO-20i (2-way 1-shot)mIoU20.4PPNet (ResNet-50)
Meta-LearningPASCAL-5i (1-Shot)Mean IoU51.5PPNet (ResNet-50)
Meta-LearningPASCAL-5i (1-Shot)learnable parameters (million)31.5PPNet (ResNet-50)
Meta-LearningCOCO-20i (1-shot)Mean IoU29PPNet (ResNet-50)
Meta-LearningCOCO-20i (1-shot)learnable parameters (million)31.5PPNet (ResNet-50)
Meta-LearningPascal5imeanIOU55.16PPNet
Meta-LearningPASCAL-5i (5-Shot)Mean IoU62PPNet (ResNet-50)
Meta-LearningPASCAL-5i (5-Shot)learnable parameters (million)31.5PPNet (ResNet-50)

Related Papers

SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction2025-07-21Deep 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 Fusion2025-07-17SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation2025-07-17Unified Medical Image Segmentation with State Space Modeling Snake2025-07-17A Privacy-Preserving Semantic-Segmentation Method Using Domain-Adaptation Technique2025-07-17