.png){kind=icon}
.png){kind=icon}
Return
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}
Share.png){kind=icon}
Save
Abstract
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.
Keywords:
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 Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.6
Papers:
9.8W
Citations:
29.4W