Mar 31, 2021 · A domain adaptive object detection transformer that introduces information fusion for effective transfer from a labeled source domain to an unlabeled target ...
The recent detection transformer (DETR) simplifies the object detection pipeline by removing hand-crafted designs and hyperparameters as employed in ...
DA-DETR is a simple yet effective domain adaptive object detection network that performs inter-domain alignment with a single discriminator and greatly ...
Mar 31, 2021 · In this work, we adopt a one-stage detector and design DA-DETR, a simple yet effective domain adaptive object detection network that performs ...
Mar 31, 2021 · DA-DETR introduces a hybrid attention module that explicitly pinpoints the hard-aligned features for simple yet effective alignment across ...
With DA-DETR [33] , transformers were applied in domain adaptation for the first time. Using hybrid self-attention modules, they improve object detection ...
(arXiv 2021.03) DA-DETR: Domain Adaptive Detection Transformer by Hybrid Attention, [Paper]; (arXiv 2021.04) Efficient DETR: Improving End-to-End Object ...
Inspired by the unique DETR attention mechanisms, DA-DETR is designed, a domain adaptive object detection transformer that introduces information fusion for ...
Missing: Hybrid | Show results with:Hybrid
Inspired by the unique DETR attention mechanisms, we design DA-DETR, a domain adaptive object detection transformer that introduces information fusion for ...
May 20, 2024 · We introduce a strong DETR-based detector named Domain Adaptive detection TRansformer (DATR) for unsupervised domain adaptation of object detection.