Significance of Softmax-Based Features in Comparison to Distance Metric Learning-Based Features.
Where this comes from
- Record sourced from PubMed, PMID 30990420.
- Also identified by DOI 10.1109/TPAMI.2019.2911075.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
End-to-end distance metric learning (DML) has been applied to obtain features useful in many computer vision tasks. However, these DML studies have not provided equitable comparisons between features extracted from DML-based networks and softmax-based networks. In this paper, we present objective comparisons between these two approaches under the same network architecture.
Medical subject headings
- Deep Learning
- Image Processing, Computer-Assisted