修复跨域少样本目标检测中的目标域散光问题
Remedying Target-Domain Astigmatism for Cross-Domain Few-Shot Object Detection
针对跨域少样本目标检测中注意力分散的问题，提出中心-外周注意力精炼框架，利用类特定原型和文本语义对齐来重塑注意力，可复用于其他域适应检测任务。
原文依据 models exhibit dispersed and unfocused attention in target domains, leading to imprecise localization and redundant predictions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论跨域少样本目标检测（CD-FSOD）旨在将预训练检测器从源域适应到标注有限的目标域，面临严重的域偏移和数据稀缺问题。本文发现了一个此前被忽视的现象：模型在目标域中表现出分散且不集中的注意力，导致定位不精确和冗余预测，就像人无法聚焦于视觉对象一样。因此，我们将其称为目标域散光问题。对Transformer各层注意力距离的分析表明，常规微调本身具有修复该问题的趋势，但结果仍远不能令人满意，本文旨在增强这一趋势。受人类中央凹式视觉系统的生物学启发，我们通过中心-外周注意力精炼框架增强微调的固有趋势，该框架包含：（1）正模式精炼模块，利用类特定原型将注意力重塑向语义对象，模拟视觉中心区域；（2）负上下文调制模块，通过建模背景上下文增强边界判别，模拟视觉外周区域；（3）文本语义对齐模块，通过跨模态线索加强中心-外周区分。我们的仿生方法将散光注意力转化为聚焦模式，显著提升了对目标域的适应能力。在六个具有挑战性的CD-FSOD基准上的实验一致表明检测精度得到提升，并确立了新的最优结果。
英文原文摘要 1613 字符
Cross-domain few-shot object detection (CD-FSOD) aims to adapt pretrained detectors from a source domain to target domains with limited annotations, suffering from severe domain shifts and data scarcity problems. In this work, we find a previously overlooked phenomenon: models exhibit dispersed and unfocused attention in target domains, leading to imprecise localization and redundant predictions, just like a human cannot focus on visual objects. Therefore, we call it the target-domain Astigmatism problem. Analysis on attention distances across transformer layers reveals that regular fine-tuning inherently shows a trend to remedy this problem, but results are still far from satisfactory, which we aim to enhance in this paper. Biologically inspired by the human fovea-style visual system, we enhance the fine-tuning's inherent trend through a center-periphery attention refinement framework, which contains (1) a Positive Pattern Refinement module to reshape attention toward semantic objects using class-specific prototypes, simulating the visual center region; (2) a Negative Context Modulation module to enhance boundary discrimination by modeling background context, simulating the visual periphery region; and (3) a Textual Semantic Alignment module to strengthen center-periphery distinction through cross-modal cues. Our bio-inspired approach transforms astigmatic attention into focused patterns, substantially improving adaptation to target domains. Experiments on six challenging CD-FSOD benchmarks consistently demonstrate improved detection accuracy and establish new state-of-the-art results.