提升Transformer检测器在分布外数据上的鲁棒性，解决领域泛化难题。
DG-DETR: Toward Domain Generalized Detection Transformer
- 通过正交投影去除查询中的领域偏差，实现无领域偏见的查询选择。
- 利用小波分解分离域不变与域特定特征，合成多样潜在风格。
- 方法简单易用，适配各类DETR模型，显著提升跨域检测性能。
基于Transformer的端到端检测器（DETR）展现出强大检测能力，但领域泛化（DG）研究主要集中在卷积神经网络（CNN）架构，对DETR的鲁棒性关注不足。本文提出一种简单、高效且可即插即用的领域泛化检测变压器（DG-DETR），显著提升DETR在分布外（OOD）数据上的鲁棒性。核心思路包括：设计一种新型无领域偏见的查询选择策略，通过将对象查询正交投影至实例级风格空间，消除领域诱导偏差；同时采用小波分解将特征解耦为域不变与域特定成分，可在保留物体语义特征的前提下合成多样化潜在风格。实验验证了该方法的有效性，代码已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。