素描
计算机科学
过度拟合
人工智能
情态动词
特征(语言学)
嵌入
代表(政治)
匹配(统计)
特征学习
模式识别(心理学)
机器学习
人工神经网络
算法
数学
语言学
化学
哲学
统计
政治
高分子化学
政治学
法学
作者
Yiyang Cai,Jiaming Lu,Jiewen Wang,Shuang Liang
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2023-07-01
卷期号:: 132-137
被引量:3
标识
DOI:10.1109/icme55011.2023.00031
摘要
In recent years, sketch-based 3D shape retrieval has attracted growing attention. While many previous studies have focused on cross-modal matching between hand-drawn sketches and 3D shapes, the critical issue of how to handle low-quality and noisy samples in sketch data has been largely neglected. This paper presents an uncertainty-aware cross-modal transfer network (UACTN) that addresses this issue. UACTN decouples the representation learning of sketches and 3D shapes into two separate tasks: classification-based sketch uncertainty learning and 3D shape feature transfer. We first introduce an end-to-end classification-based approach that simultaneously learns sketch features and uncertainty, allowing uncertainty to prevent overfitting noisy sketches by assigning different levels of importance to clean and noisy sketches. Then, 3D shape features are mapped into the pre-learned sketch embedding space for feature alignment. Extensive experiments and ablation studies on two benchmarks demonstrate the superiority of our proposed method compared to state-of-the-art methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI