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

Showing 76100 of 168 papers

TitleStatusHype
FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware NetworkCode1
Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network0
SegGPT: Towards Segmenting Everything in Context0
MSI: Maximize Support-Set Information for Few-Shot SegmentationCode0
Mask Matching Transformer for Few-Shot SegmentationCode1
Prototype as Query for Few Shot Semantic SegmentationCode1
A Strong Baseline for Generalized Few-Shot Semantic SegmentationCode1
Progressively Dual Prior Guided Few-shot Semantic Segmentation0
Interclass Prototype Relation for Few-Shot Segmentation0
PatchRefineNet: Improving Binary Segmentation by Incorporating Signals from Optimal Patch-wise BinarizationCode0
Self-Regularized Prototypical Network for Few-Shot Semantic Segmentation0
Prediction Calibration for Generalized Few-shot Semantic Segmentation0
Feature-Proxy Transformer for Few-Shot SegmentationCode1
Intermediate Prototype Mining Transformer for Few-Shot Semantic SegmentationCode1
Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes0
Doubly Deformable Aggregation of Covariance Matrices for Few-shot SegmentationCode1
Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representation0
Self-Support Few-Shot Semantic SegmentationCode1
Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot SegmentationCode1
Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot SegmentationCode1
MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot SegmentationCode1
Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuningCode1
Learning Non-target Knowledge for Few-shot Semantic SegmentationCode1
Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation0
Beyond the Prototype: Divide-and-conquer Proxies for Few-shot SegmentationCode1
Show:102550
← PrevPage 4 of 7Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SegGPT (ViT)Mean IoU83.2Unverified
2PGMA-Net (ResNet-101)Mean IoU77.6Unverified
3DCAMA (ResNet-101)FB-IoU77.6Unverified
4PGMA-Net (ResNet-50)Mean IoU74.1Unverified
5PGMA-Net (ViT-B/16)Mean IoU74.1Unverified
6GF-SAM (DINOv2)Mean IoU72.1Unverified
7HMNet (ResNet-50)Mean IoU70.4Unverified
8AENet (ResNet-50)Mean IoU70.3Unverified
9HDMNet (DifFSS, ResNet-50)Mean IoU70.2Unverified
10VAT + MSI (ResNet-101)Mean IoU70.1Unverified
#ModelMetricClaimedVerifiedStatus
1SegGPT (ViT)Mean IoU89.8Unverified
2GF-SAM (DINOv2)Mean IoU82.6Unverified
3PGMA-Net (ResNet-101)Mean IoU78.6Unverified
4FPTrans (DeiT-B/16)Mean IoU78Unverified
5DGPNet (ResNet-101)Mean IoU75.4Unverified
6PGMA-Net (ResNet-50)Mean IoU75.2Unverified
7DCAMA (Swin-B)Mean IoU74.9Unverified
8PGMA-Net (ViT-B/16)Mean IoU74.6Unverified
9AENet (ResNet-50)Mean IoU74.2Unverified
10HMNet (ResNet-50)Mean IoU74.1Unverified