NCJ Number
254594
Date Published
2019
Length
9 pages
Annotation
For convolutional neural network models that optimize an image embedding, this article proposes a method to highlight the regions of images that contribute most to pairwise similarity.
Abstract
This work is a corollary to the visualization tools developed for classification networks, but applicable to the problem domains better suited to similarity learning. The visualization shows how similarity networks that are fine-tuned learn to focus on different features. This approach is generalized to embedding networks that use different pooling strategies and provides a simple mechanism to support image similarity searches on objects or sub-regions in the query image. (publisher abstract modified)
Date Published: January 1, 2019
Downloads
Similar Publications
- The Collection, Preservation, and Processing of DNA Samples from Decomposing Human Remains for More Direct Disaster Victim Identification (DVI)
- A Virtual Anthropological Approach to the Study of Commingled Human Remains
- Detection of Synthetic Cathinones in Seized Drugs Using Surface-enhanced Raman Spectroscopy (SERS)