Low-Resolution Object Recognition with Cross-Resolution Relational Contrastive Distillation

TL;DR

This paper introduces a cross-resolution relational contrastive distillation method that improves low-resolution object recognition by better transferring knowledge from high-resolution models, especially under significant representation discrepancies.

Contribution

The proposed approach enhances low-resolution recognition by preserving relational structures through contrastive distillation, addressing training-testing discrepancies.

Findings

Significant improvement in low-resolution object classification accuracy.

Enhanced face recognition performance in low-resolution scenarios.

Effective knowledge transfer demonstrated through extensive experiments.

Abstract

Recognizing objects in low-resolution images is a challenging task due to the lack of informative details. Recent studies have shown that knowledge distillation approaches can effectively transfer knowledge from a high-resolution teacher model to a low-resolution student model by aligning cross-resolution representations. However, these approaches still face limitations in adapting to the situation where the recognized objects exhibit significant representation discrepancies between training and testing images. In this study, we propose a cross-resolution relational contrastive distillation approach to facilitate low-resolution object recognition. Our approach enables the student model to mimic the behavior of a well-trained teacher model which delivers high accuracy in identifying high-resolution objects. To extract sufficient knowledge, the student learning is supervised with contrastive relational distillation loss, which preserves the similarities in various relational structures in contrastive representation space. In this manner, the capability of recovering missing details of familiar low-resolution objects can be effectively enhanced, leading to a better knowledge transfer. Extensive experiments on low-resolution object classification and low-resolution face recognition clearly demonstrate the effectiveness and adaptability of our approach.