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/A Strong Baseline for Generalized Few-Shot Semantic Segmen...

A Strong Baseline for Generalized Few-Shot Semantic Segmentation

Sina Hajimiri, Malik Boudiaf, Ismail Ben Ayed, Jose Dolz

2022-11-25CVPR 2023 1SegmentationFew-Shot Semantic SegmentationSemantic Segmentation
PaperPDFCodeCode(official)

Abstract

This paper introduces a generalized few-shot segmentation framework with a straightforward training process and an easy-to-optimize inference phase. In particular, we propose a simple yet effective model based on the well-known InfoMax principle, where the Mutual Information (MI) between the learned feature representations and their corresponding predictions is maximized. In addition, the terms derived from our MI-based formulation are coupled with a knowledge distillation term to retain the knowledge on base classes. With a simple training process, our inference model can be applied on top of any segmentation network trained on base classes. The proposed inference yields substantial improvements on the popular few-shot segmentation benchmarks, PASCAL-$5^i$ and COCO-$20^i$. Particularly, for novel classes, the improvement gains range from 7% to 26% (PASCAL-$5^i$) and from 3% to 12% (COCO-$20^i$) in the 1-shot and 5-shot scenarios, respectively. Furthermore, we propose a more challenging setting, where performance gaps are further exacerbated. Our code is publicly available at https://github.com/sinahmr/DIaM.

Results

TaskDatasetMetricValueModel
Few-Shot LearningPASCAL-5i (1-Shot)Mean Base and Novel53DIaM (ResNet-50)
Few-Shot LearningPASCAL-5i (1-Shot)Mean IoU61.95DIaM (ResNet-50)
Few-Shot LearningPASCAL-5i (5-Shot)Mean Base and Novel63.08DIaM (ResNet-50)
Few-Shot LearningPASCAL-5i (5-Shot)Mean IoU66.97DIaM (ResNet-50)
Few-Shot LearningCOCO-20i (5-shot)Mean Base and Novel38.55DIaM (ResNet-50)
Few-Shot LearningCOCO-20i (5-shot)Mean IoU43.46DIaM (ResNet-50)
Few-Shot LearningCOCO-20i (1-shot)Mean Base and Novel32.75DIaM (ResNet-50)
Few-Shot LearningCOCO-20i (1-shot)Mean IoU40.52DIaM (ResNet-50)
Few-Shot Semantic SegmentationPASCAL-5i (1-Shot)Mean Base and Novel53DIaM (ResNet-50)
Few-Shot Semantic SegmentationPASCAL-5i (1-Shot)Mean IoU61.95DIaM (ResNet-50)
Few-Shot Semantic SegmentationPASCAL-5i (5-Shot)Mean Base and Novel63.08DIaM (ResNet-50)
Few-Shot Semantic SegmentationPASCAL-5i (5-Shot)Mean IoU66.97DIaM (ResNet-50)
Few-Shot Semantic SegmentationCOCO-20i (5-shot)Mean Base and Novel38.55DIaM (ResNet-50)
Few-Shot Semantic SegmentationCOCO-20i (5-shot)Mean IoU43.46DIaM (ResNet-50)
Few-Shot Semantic SegmentationCOCO-20i (1-shot)Mean Base and Novel32.75DIaM (ResNet-50)
Few-Shot Semantic SegmentationCOCO-20i (1-shot)Mean IoU40.52DIaM (ResNet-50)
Meta-LearningPASCAL-5i (1-Shot)Mean Base and Novel53DIaM (ResNet-50)
Meta-LearningPASCAL-5i (1-Shot)Mean IoU61.95DIaM (ResNet-50)
Meta-LearningPASCAL-5i (5-Shot)Mean Base and Novel63.08DIaM (ResNet-50)
Meta-LearningPASCAL-5i (5-Shot)Mean IoU66.97DIaM (ResNet-50)
Meta-LearningCOCO-20i (5-shot)Mean Base and Novel38.55DIaM (ResNet-50)
Meta-LearningCOCO-20i (5-shot)Mean IoU43.46DIaM (ResNet-50)
Meta-LearningCOCO-20i (1-shot)Mean Base and Novel32.75DIaM (ResNet-50)
Meta-LearningCOCO-20i (1-shot)Mean IoU40.52DIaM (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