Counterfactual Balancing Feature Alignment for Few-Shot Cross-Domain Scene Parsing

Scene parsing becomes a key step to develop a visual autonomous driver. Real-world images are too expansive to annotate at scale, while few-shot cross-domain scene parsing (CSP) approaches only require a few labeled target images to train a model with source virtual data, thus, attracting more atten...

Description complète

Détails bibliographiques

Auteurs principaux:	Cody Mingzhan Sun, Ziliang Chen, Liang Lin
Format:	Artigo
Langue:	Inglês
Publié:	IEEE 2025-01-01
Collection:	IEEE Access
Sujets:	Computer vision few-shot domain adaptation urban scene parsing semantic segmentation Rubin causality
Accès en ligne:	https://ieeexplore.ieee.org/document/10089460/
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!