Enhancing Fine-Grained Classification for Low Resolution Images

TL;DR

This paper introduces a novel attribute-assisted loss function to improve fine-grained classification accuracy on low resolution images by leveraging ancillary attribute information, addressing the challenge of limited detail in such images.

Contribution

It proposes a new loss function that incorporates attribute-level information to enhance discriminative feature learning for low resolution fine-grained classification.

Findings

The method improves classification accuracy across multiple datasets.

The approach is effective for images from 32x32 to 224x224 resolutions.

Experimental results demonstrate significant gains over baseline models.

Abstract

Low resolution fine-grained classification has widespread applicability for applications where data is captured at a distance such as surveillance and mobile photography. While fine-grained classification with high resolution images has received significant attention, limited attention has been given to low resolution images. These images suffer from the inherent challenge of limited information content and the absence of fine details useful for sub-category classification. This results in low inter-class variations across samples of visually similar classes. In order to address these challenges, this research proposes a novel attribute-assisted loss, which utilizes ancillary information to learn discriminative features for classification. The proposed loss function enables a model to learn class-specific discriminative features, while incorporating attribute-level separability. Evaluation is performed on multiple datasets with different models, for four resolutions varying from 32x32 to 224x224. Different experiments demonstrate the efficacy of the proposed attributeassisted loss for low resolution fine-grained classification.