DeriveNet for (Very) Low Resolution Image Classification

Images captured from a distance often result in (very) low resolution (VLR/LR) region of interest, requiring automated identification. VLR/LR images (or regions of interest) often contain less information content, rendering ineffective feature extraction and classification. To this effect, this rese...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2022-10, Vol.44 (10), p.6569-6577
Main Authors: Singh, Maneet, Nagpal, Shruti, Singh, Richa, Vatsa, Mayank
Format: Article
Language:English
Subjects:
Classification
Datasets
digit classification
Domains
Face recognition
Feature extraction
Image classification
Image recognition
Image reconstruction
Image resolution
Learning
Task analysis
Training
Very low resolution classification
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Images captured from a distance often result in (very) low resolution (VLR/LR) region of interest, requiring automated identification. VLR/LR images (or regions of interest) often contain less information content, rendering ineffective feature extraction and classification. To this effect, this research proposes a novel DeriveNet model for VLR/LR classification, which focuses on learning effective class boundaries by utilizing the class-specific domain knowledge. DeriveNet model is jointly trained via two losses: (i) proposed Derived-Margin softmax loss and (ii) the proposed Reconstruction-Center (ReCent) loss. The Derived-Margin softmax loss focuses on learning an effective VLR classifier while explicitly modeling the inter-class variations. The ReCent loss incorporates domain information by learning a HR reconstruction space for approximating the class variations for the VLR/LR samples. It is utilized to derive inter-class margins for the Derived-Margin softmax loss. The DeriveNet model has been trained with a novel Multi-resolution Pyramid based data augmentation which enables the model to learn from varying resolutions during training. Experiments and analysis have been performed on multiple datasets for (i) VLR/LR face recognition, (ii) VLR digit classification, and (iii) VLR/LR face recognition from drone-shot videos. The DeriveNet model achieves state-of-the-art performance across different datasets, thus promoting its utility for several VLR/LR classification tasks.
ISSN:0162-8828
2160-9292
1939-3539
DOI:10.1109/TPAMI.2021.3088756