提出CSDN检测头，让模型像人一样聚焦目标、感知环境，提升小目标和多尺寸物体检测能力。
CSDN: A Context-Gated Self-Adaptive Detection Network for Real-Time Object Detection
- 受人类视觉启发，设计上下文门控自适应检测头
- 在COCO数据集上比原模型提升2.1个点的AP
- 可直接替换主流检测器头部，微调即可生效
卷积神经网络（CNN）长期作为目标检测的基石，但受限于有限的感受野，难以捕捉全局上下文信息。我们重新审视了DETR启发的检测头，发现其自注意力模块存在显著冗余。为此，提出基于Transformer的上下文门控自适应检测网络（CSDN），灵感来自人类视觉：观察物体时，会聚焦某一点，感知周围环境，并扫视物体整体。该机制使每个感兴趣区域（ROI）能自适应选择并融合不同尺度与特征维度的信息。CSDN具备更强的全局上下文建模能力，能更好适应不同尺寸和结构的目标。所提检测头可直接替换多种基于CNN的检测器的原始头部，仅需对预训练权重进行少量微调，便能显著提升检测精度。
原文摘要 · Abstract (English)
Convolutional neural networks (CNNs) have long been the cornerstone of target detection, but they are often limited by limited receptive fields, which hinders their ability to capture global contextual information. We re-examined the DETR-inspired detection head and found substantial redundancy in its self-attention module. To solve these problems, we introduced the Context-Gated Scale-Adaptive Detection Network (CSDN), a Transformer-based detection header inspired by human visual perception: when observing an object, we always concentrate on one site, perceive the surrounding environment, and glance around the object. This mechanism enables each region of interest (ROI) to adaptively select and combine feature dimensions and scale information from different patterns. CSDN provides more powerful global context modeling capabilities and can better adapt to objects of different sizes and structures. Our proposed detection head can directly replace the native heads of various CNN-based detectors, and only a few rounds of fine-tuning on the pre-trained weights can significantly improve the detection accuracy.
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。