CD-FKD: Cross-Domain Feature Knowledge Distillation for Robust Single-Domain Generalization in Object Detection
This addresses robust object detection for applications like autonomous driving and surveillance, but it is incremental as it builds on existing knowledge distillation and data augmentation techniques.
The paper tackles the problem of single-domain generalization in object detection by proposing Cross-Domain Feature Knowledge Distillation (CD-FKD), which uses diversified data and feature distillation to improve robustness to domain shifts like weather and lighting changes, resulting in outperforming state-of-the-art methods in target and source domain performance.
Single-domain generalization is essential for object detection, particularly when training models on a single source domain and evaluating them on unseen target domains. Domain shifts, such as changes in weather, lighting, or scene conditions, pose significant challenges to the generalization ability of existing models. To address this, we propose Cross-Domain Feature Knowledge Distillation (CD-FKD), which enhances the generalization capability of the student network by leveraging both global and instance-wise feature distillation. The proposed method uses diversified data through downscaling and corruption to train the student network, whereas the teacher network receives the original source domain data. The student network mimics the features of the teacher through both global and instance-wise distillation, enabling it to extract object-centric features effectively, even for objects that are difficult to detect owing to corruption. Extensive experiments on challenging scenes demonstrate that CD-FKD outperforms state-of-the-art methods in both target domain generalization and source domain performance, validating its effectiveness in improving object detection robustness to domain shifts. This approach is valuable in real-world applications, like autonomous driving and surveillance, where robust object detection in diverse environments is crucial.