Few-Shot Semantic Segmentation

Few-Shot Semantic Segmentation (FSS) focuses on segmenting novel object categories from only a handful of annotated examples. Most existing approaches rely on extensive episodic training to learn transferable representat…

Revealing the Semantic Selection Gap in DINOv3 through Training-Free Few-Shot Segmentation

2026-02-07 · Hussni Mohd Zakir, Eric Tatt Wei Ho arxiv

Recent self-supervised Vision Transformers (ViTs), such as DINOv3, provide rich feature representations for dense vision tasks. This study investigates the intrinsic few-shot semantic segmentation (FSS) capabilities of f…

Few-Shot Semantic Segmentation Test-time Adaptation

AI-Based Culvert-Sewer Inspection

2026-01-21 · Christina Thrainer arxiv

Culverts and sewer pipes are critical components of drainage systems, and their failure can lead to serious risks to public safety and the environment. In this thesis, we explore methods to improve automated defect segme…

Few-Shot Semantic Segmentation Few-Shot Learning Data Augmentation

SAM-Aug: Leveraging SAM Priors for Few-Shot Parcel Segmentation in Satellite Time Series

2026-01-14 · Kai Hu, Yaozu Feng, Vladimir Lysenko, Ya Guo 외 arxiv

Few-shot semantic segmentation of time-series remote sensing images remains a critical challenge, particularly in regions where labeled data is scarce or costly to obtain. While state-of-the-art models perform well under…

Few-Shot Semantic Segmentation Temporal Sequences

Take a Peek: Efficient Encoder Adaptation for Few-Shot Semantic Segmentation via LoRA

2025-12-11 · Pasquale De Marinis, Gennaro Vessio, Giovanna Castellano arxiv

Few-shot semantic segmentation (FSS) aims to segment novel classes in query images using only a small annotated support set. While prior research has mainly focused on improving decoders, the encoder's limited ability to…

Few-Shot Semantic Segmentation Computational Efficiency

Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Design

2025-11-22 · Pasquale De Marinis, Uzay Kaymak, Rogier Brussee, Gennaro Vessio 외 arxiv

Few-Shot Semantic Segmentation (FSS) models achieve strong performance in segmenting novel classes with minimal labeled examples, yet their decision-making processes remain largely opaque. While explainable AI has advanc…

Few-Shot Semantic Segmentation

전체 180편 보기 →

Few-Shot Semantic Segmentation

Benchmarks

PASCAL-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

Pascal5i

Most implemented

PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment

Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation

SegGPT: Segmenting Everything In Context

Prior Guided Feature Enrichment Network for Few-Shot Segmentation

A Strong Baseline for Generalized Few-Shot Semantic Segmentation

Feature-Proxy Transformer for Few-Shot Segmentation

Papers