GCA-SUNet: A Gated Context-Aware Swin-UNet for Exemplar-Free Counting
This addresses the challenge of counting objects in images without predefined categories or exemplars, which is useful for applications like crowd or vehicle counting, but appears incremental as it builds on existing Swin-UNet architectures.
The paper tackles the problem of exemplar-free counting, aiming to count objects without intensive annotations, by proposing GCA-SUNet, which uses gated context-aware mechanisms and Swin transformers to map images to density maps, achieving significant and consistent outperformance over state-of-the-art methods on datasets like FSC-147 and CARPK.
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.