Localization-Aware Adaptive Pairwise Margin Loss for Fine-Grained Image Recognition

Localization-Aware Adaptive Pairwise Margin Loss for Fine-Grained Image Recognition

Fine-grained image recognition is a highly challenging problem due to subtle differences between images. There are many attempts to solve fine-grained image recognition problems using data augmentation, jointly optimizing deep metric learning. CutMix is one of the excellent data augmentation strateg...

Full description

Bibliographic Details
Main Authors: Taehung Kim, Hoseong Kim, Hyeran Byun
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Adaptive margin
deep neural networks
fine-grained image recognition
metric learning
image augmentation
image generation
Online Access:https://ieeexplore.ieee.org/document/9313990/

Internet

https://ieeexplore.ieee.org/document/9313990/

Similar Items