无需标注样本，直接生成密度图实现精准计数。
GCA-SUNet: A Gated Context-Aware Swin-UNet for Exemplar-Free Counting
- 用门控机制抑制无关背景，利用自相似性聚焦目标对象。
- 在FSC-147和CARPK数据集上超越现有方法，提升显著且稳定。
- 适合无类别先验、无样本标注的复杂场景计数任务。
无样本计数旨在不依赖物体或样本密集标注的情况下统计目标物体数量。为此，我们提出门控上下文感知Swin-UNet（GCA-SUNet），直接将输入图像映射为可计数物体的密度图。具体而言，一组Swin变换器构成编码器以提取鲁棒特征表示；设计门控上下文感知调制模块，通过门控机制抑制无关物体或背景，并利用自相似矩阵挖掘目标物体间的注意力关联。该门控策略还被引入到Swin-UNet的瓶颈网络与解码器中，突出最相关特征。通过显式利用可计数物体间的注意力支持并借助门控机制消除无关特征，GCA-SUNet无需依赖预定义类别或样本即可专注计数目标物体。在真实世界数据集FSC-147和CARPK上的实验结果表明，GCA-SUNet显著且一致地优于当前最优方法。代码已公开于https://github.com/Amordia/GCA-SUNet。
原文摘要 · Abstract (English)
Exemplar-Free Counting aims to count objects of interest without intensive annotations of objects or exemplars. To achieve this, we propose a Gated Context-Aware Swin-UNet (GCA-SUNet) to directly map an input image to the density map of countable objects. Specifically, a set of Swin transformers form an encoder to derive a robust feature representation, and a Gated Context-Aware Modulation block is designed to suppress irrelevant objects or background through a gate mechanism and exploit the attentive support of objects of interest through a self-similarity matrix. The gate strategy is also incorporated into the bottleneck network and the decoder of the Swin-UNet to highlight the features most relevant to objects of interest. By explicitly exploiting the attentive support among countable objects and eliminating irrelevant features through the gate mechanisms, the proposed GCA-SUNet focuses on and counts objects of interest without relying on predefined categories or exemplars. Experimental results on the real-world datasets such as FSC-147 and CARPK demonstrate that GCA-SUNet significantly and consistently outperforms state-of-the-art methods. The code is available at https://github.com/Amordia/GCA-SUNet.
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。