SOTAVerified

Few-Shot Semantic Segmentation

Few-shot semantic segmentation (FSS) learns to segment target objects in query image given few pixel-wise annotated support image.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 168 papers

TitleStatusHype
Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation—0
DINOv2-powered Few-Shot Semantic Segmentation: A Unified Framework via Cross-Model Distillation and 4D Correlation Mining—0
FSSUWNet: Mitigating the Fragility of Pre-trained Models with Feature Enhancement for Few-Shot Semantic Segmentation in Underwater ImagesCode0
Exploring Few-Shot Defect Segmentation in General Industrial Scenarios with Metric Learning and Vision Foundation ModelsCode0
AdaSemSeg: An Adaptive Few-shot Semantic Segmentation of Seismic Facies—0
Overcoming Support Dilution for Robust Few-shot Semantic Segmentation—0
Few-shot Structure-Informed Machinery Part Segmentation with Foundation Models and Graph Neural NetworksCode1
DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentation—0
AFANet: Adaptive Frequency-Aware Network for Weakly-Supervised Few-Shot Semantic SegmentationCode1
Enhancing Generalized Few-Shot Semantic Segmentation via Effective Knowledge TransferCode0
FAMNet: Frequency-aware Matching Network for Cross-domain Few-shot Medical Image SegmentationCode2
Generative Model-Based Fusion for Improved Few-Shot Semantic Segmentation of Infrared Images—0
Is Foreground Prototype Sufficient? Few-Shot Medical Image Segmentation with Background-Fused Prototype—0
Segment Any Class (SAC): Multi-Class Few-Shot Semantic Segmentation via Class Region Proposals—0
Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic SegmentationCode1
Task Consistent Prototype Learning for Incremental Few-shot Semantic Segmentation—0
Bridge the Points: Graph-based Few-shot Segment Anything SemanticallyCode1
Unleashing the Potential of the Diffusion Model in Few-shot Semantic SegmentationCode1
RobustEMD: Domain Robust Matching for Cross-domain Few-shot Medical Image SegmentationCode0
Hybrid Mamba for Few-Shot SegmentationCode1
A Surprisingly Simple Approach to Generalized Few-Shot Semantic SegmentationCode0
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided PrototypingCode1
Generalized Few-Shot Semantic Segmentation in Remote Sensing: Challenge and BenchmarkCode1
Foundation Model or Finetune? Evaluation of few-shot semantic segmentation for river pollutionCode0
TeFF: Tracking-enhanced Forgetting-free Few-shot 3D LiDAR Semantic SegmentationCode0
Applying ViT in Generalized Few-shot Semantic SegmentationCode0
Localization and Expansion: A Decoupled Framework for Point Cloud Few-shot Semantic Segmentation—0
Small Object Few-shot Segmentation for Vision-based Industrial InspectionCode1
Eliminating Feature Ambiguity for Few-Shot SegmentationCode1
Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual PromptsCode2
Few-Shot Medical Image Segmentation with High-Fidelity PrototypesCode1
Label-Efficient Semantic Segmentation of LiDAR Point Clouds in Adverse Weather ConditionsCode1
APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation—0
Memory-guided Network with Uncertainty-based Feature Augmentation for Few-shot Semantic Segmentation—0
Organizing Background to Explore Latent Classes for Incremental Few-shot Semantic Segmentation—0
Cross-Domain Few-Shot Semantic Segmentation via Doubly Matching TransformationCode1
Few-Shot Fruit Segmentation via Transfer LearningCode0
Show and Grasp: Few-shot Semantic Segmentation for Robot Grasping through Zero-shot Foundation Models—0
Domain-Rectifying Adapter for Cross-Domain Few-Shot SegmentationCode1
Learnable Prompt for Few-Shot Semantic Segmentation in Remote Sensing DomainCode1
LERENet: Eliminating Intra-class Differences for Metal Surface Defect Few-shot Semantic Segmentation—0
A Novel Benchmark for Few-Shot Semantic Segmentation in the Era of Foundation ModelsCode1
Boosting Few-Shot Semantic Segmentation Via Segment Anything Model—0
Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship DescriptorsCode0
Analyzing Local Representations of Self-supervised Vision Transformers—0
Relevant Intrinsic Feature Enhancement Network for Few-Shot Semantic Segmentation—0
Background Clustering Pre-training for Few-shot Segmentation—0
Language-guided Few-shot Semantic Segmentation—0
Self-guided Few-shot Semantic Segmentation for Remote Sensing Imagery Based on Large Vision Models—0
Target-aware Bi-Transformer for Few-shot Segmentation—0
Show:102550
← PrevPage 1 of 4Next →
All datasetsPASCAL-5i (1-Shot)PASCAL-5i (5-Shot)COCO-20i (1-shot)COCO-20i (5-shot)FSS-1000 (1-shot)FSS-1000 (5-shot)COCO-20i -> Pascal VOC (1-shot)COCO-20i -> Pascal VOC (5-shot)COCO-20i (2-way 1-shot)COCO-20i (10-shot)PASCAL-5i (10-Shot)FSS-1000

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SegGPT (ViT)Mean IoU83.2—Unverified
2DCAMA (ResNet-101)FB-IoU77.6—Unverified
3PGMA-Net (ResNet-101)Mean IoU77.6—Unverified
4PGMA-Net (ResNet-50)Mean IoU74.1—Unverified
5PGMA-Net (ViT-B/16)Mean IoU74.1—Unverified
6GF-SAM (DINOv2)Mean IoU72.1—Unverified
7HMNet (ResNet-50)Mean IoU70.4—Unverified
8AENet (ResNet-50)Mean IoU70.3—Unverified
9HDMNet (DifFSS, ResNet-50)Mean IoU70.2—Unverified
10VAT + MSI (ResNet-101)Mean IoU70.1—Unverified
#ModelMetricClaimedVerifiedStatus
1SegGPT (ViT)Mean IoU89.8—Unverified
2GF-SAM (DINOv2)Mean IoU82.6—Unverified
3PGMA-Net (ResNet-101)Mean IoU78.6—Unverified
4FPTrans (DeiT-B/16)Mean IoU78—Unverified
5DGPNet (ResNet-101)Mean IoU75.4—Unverified
6PGMA-Net (ResNet-50)Mean IoU75.2—Unverified
7DCAMA (Swin-B)Mean IoU74.9—Unverified
8PGMA-Net (ViT-B/16)Mean IoU74.6—Unverified
9AENet (ResNet-50)Mean IoU74.2—Unverified
10HMNet (ResNet-50)Mean IoU74.1—Unverified