Low-Resolution Object Recognition with Cross-Resolution Relational Contrastive Distillation
This work addresses the problem of recognizing objects in low-resolution images for computer vision applications, representing an incremental improvement over existing knowledge distillation approaches.
The paper tackles low-resolution object recognition by proposing a cross-resolution relational contrastive distillation method to transfer knowledge from a high-resolution teacher model to a low-resolution student model, resulting in enhanced performance on classification and face recognition tasks as demonstrated in extensive experiments.
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.