Guardado en:
Detalles Bibliográficos
Autores principales: Hwang, Seongmin, Han, Daeyoung, Jeon, Moongu
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2504.19574
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Tabla de Contenidos:
  • End-to-end Transformer-based detectors (DETRs) have demonstrated strong detection performance. However, domain generalization (DG) research has primarily focused on convolutional neural network (CNN)-based detectors, while paying little attention to enhancing the robustness of DETRs. In this letter, we introduce a Domain Generalized DEtection TRansformer (DG-DETR), a simple, effective, and plug-and-play method that improves out-of-distribution (OOD) robustness for DETRs. Specifically, we propose a novel domain-agnostic query selection strategy that removes domain-induced biases from object queries via orthogonal projection onto the instance-specific style space. Additionally, we leverage a wavelet decomposition to disentangle features into domain-invariant and domain-specific components, enabling synthesis of diverse latent styles while preserving the semantic features of objects. Experimental results validate the effectiveness of DG-DETR. Our code is available at https://github.com/sminhwang/DG-DETR.