Enhancing Fine-Grained Classification for Low Resolution Images
This addresses a practical problem for applications like surveillance and mobile photography where image resolution is limited, representing an incremental improvement in a niche area.
The paper tackles the problem of fine-grained classification for low-resolution images, which lack detailed information and have low inter-class variation, by proposing a novel attribute-assisted loss that learns discriminative features, showing efficacy across multiple datasets and resolutions from 32x32 to 224x224.
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.