.png){kind=icon}
返回
On Sensitive Minima in Margin-Based Deep Distance Learning
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2020.3013560.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper investigates sensitive minima in popular deep distance learning techniques such as Siamese and Triplet networks. We demonstrate that standard formulations may find solutions that are sensitive to small changes and thus do not generalize well. To alleviate sensitive minima we propose a new approach to regularize margin-based deep distance learning by introducing stochasticity in the loss that encourages robust solutions. Our experimental results on HPatches show promise compared to common regularization techniques including weight decay and dropout, especially for small sample sizes.
Keyword:
Computer aided instruction
Robustness
Fasteners
Artificial neural networks
Measurement
Training
Two dimensional displays
Deep metric learning
regularization
generalization
feature point matching
contrastive loss
triplet loss
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Quantitative Evaluation of Collagen Crosslinks and Corresponding Tensile Mechanical Properties in Mouse Cervical Tissue during Normal Pregnancy.png)
PLoS ONE
OAAI
PLoS ONEIF0
OAAI分享收藏1H-MR spectroscopy differentiates mild cognitive impairment from normal brain agingNeuroreport
NeuroreportIF0
PREAI
分享收藏
查看更多内容