← Search

Charalambos Poullis

2 accepted papers

2026

Data Leakage Detection and De-duplication in Large Scale Geospatial Image Datasets

CVPR 2026

In our study, we conducted a comprehensive analysis of three widely used datasets in the domain of building footprint extraction using deep neural networks: the INRIA Aerial Image Labelling dataset, SpaceNet 2: Building Detection v2, and the AICrowd Mapping Challenge datasets. Our experiments reveal

Cited by 0SourcecodeScholar
2025

DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentation

CVPR 2025poster

Few-shot semantic segmentation (FSS) aims to enable models to segment novel/unseen object classes using only a limited number of labeled examples. However, current FSS methods frequently struggle with generalization due to incomplete and biased feature representations, especially when support images…