DA-Mamba：基于域自适应混合Mamba-Transformer的一阶段目标检测
DA-Mamba: Domain Adaptive Hybrid Mamba-Transformer Based One-Stage Object Detection
AI总结：
本文提出首个基于域自适应Mamba的一阶段目标检测模型DA-Mamba，通过混合Mamba-Transformer架构、熵知识蒸馏和熵驱动门控注意力实现高效跨域特征对齐与泛化。
摘要：
近年来基于2D CNN的域自适应方法由于感受野有限，难以建模长距离依赖，因此在目标域空间分布变化显著时难以有效适配。虽然基于Transformer的域自适应方法通过自注意力机制能够更好地捕捉远距离关系，从而促进更有效的跨域特征对齐，但其二次计算复杂度使得在多样域的目标检测任务中实际部署面临挑战。受Mamba架构的全局建模能力和线性计算复杂度启发，我们提出了首个基于域自适应Mamba的一阶段目标检测模型，称为DA-Mamba。具体而言，我们将Mamba的高效状态空间建模与注意力机制相结合，以应对域特定的空间和通道维度变化。我们的设计在Mamba块内利用域自适应空间和通道扫描来提取高度可迁移的表示，以实现高效的顺序处理，同时通过交叉注意力模块生成长距离的混合域空间特征，从而实现跨域的鲁棒软对齐。此外，基于混合架构在域自适应任务中会引入特征噪声这一观察，我们提出了一种基于熵的知识蒸馏框架，并引入margin ReLU，通过抑制不相关激活并对齐源域和目标域之间的不确定性来自适应地细化多级表示。最后，为了防止交叉注意力机制生成的混合特征导致过拟合，我们提出了带有随机扰动的熵驱动门控注意力，该机制同时细化目标特征并增强模型泛化能力。
英文摘要：
Recent 2D CNN-based domain adaptation approaches struggle with long-range dependencies due to limited receptive fields, making it difficult to adapt to target domains with significant spatial distribution changes. While transformer-based domain adaptation methods better capture distant relationships through self-attention mechanisms that facilitate more effective cross-domain feature alignment, their quadratic computational complexity makes practical deployment challenging for object detection tasks across diverse domains. Inspired by the global modeling and linear computation complexity of the Mamba architecture, we present the first domain-adaptive Mamba-based one-stage object detection model, termed DA-Mamba. Specifically, we combine Mamba's efficient state-space modeling with attention mechanisms to address domain-specific spatial and channel-wise variations. Our design leverages domain-adaptive spatial and channel-wise scanning within the Mamba block to extract highly transferable representations for efficient sequential processing, while cross-attention modules generate long-range, mixed-domain spatial features to enable robust soft alignment across domains. Besides, motivated by the observation that hybrid architectures introduce feature noise in domain adaptation tasks, we propose an entropy-based knowledge distillation framework with margin ReLU, which adaptively refines multi-level representations by suppressing irrelevant activations and aligning uncertainty across source and target domains. Finally, to prevent overfitting caused by the mixed-up features generated through cross-attention mechanisms, we propose entropy-driven gating attention with random perturbations that simultaneously refine target features and enhance model generalization.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
