Generalized-Scale Object Counting with Gradual Query Aggregation
This addresses the challenge of accurately counting and detecting objects of varying scales in images, which is crucial for applications like surveillance and crowd analysis, representing a significant improvement over existing methods.
The paper tackles the problem of few-shot object counting and detection across diverse object sizes and densely populated regions, proposing GECO2 which surpasses state-of-the-art methods by 10% in accuracy while running 3x faster with lower GPU memory usage.
Few-shot detection-based counters estimate the number of instances in the image specified only by a few test-time exemplars. A common approach to localize objects across multiple sizes is to merge backbone features of different resolutions. Furthermore, to enable small object detection in densely populated regions, the input image is commonly upsampled and tiling is applied to cope with the increased computational and memory requirements. Because of these ad-hoc solutions, existing counters struggle with images containing diverse-sized objects and densely populated regions of small objects. We propose GECO2, an end-to-end few-shot counting and detection method that explicitly addresses the object scale issues. A new dense query representation gradually aggregates exemplar-specific feature information across scales that leads to high-resolution dense queries that enable detection of large as well as small objects. GECO2 surpasses state-of-the-art few-shot counters in counting as well as detection accuracy by 10% while running 3x times faster at smaller GPU memory footprint.