Dilated-Scale-Aware Attention ConvNet For Multi-Class Object Counting
This work is significant for computer vision researchers and practitioners working on object counting in real-world scenarios, offering an incremental improvement in multi-class counting efficiency.
This paper addresses multi-class object counting using point-level annotations, a more efficient approach than bounding box annotations. The proposed network achieves state-of-the-art performance on challenging benchmarks by modifying the output channel to accommodate multiple categories and introducing a multi-mask structure to mitigate feature interference.
Object counting aims to estimate the number of objects in images. The leading counting approaches focus on the single category counting task and achieve impressive performance. Note that there are multiple categories of objects in real scenes. Multi-class object counting expands the scope of application of object counting task. The multi-target detection task can achieve multi-class object counting in some scenarios. However, it requires the dataset annotated with bounding boxes. Compared with the point annotations in mainstream object counting issues, the coordinate box-level annotations are more difficult to obtain. In this paper, we propose a simple yet efficient counting network based on point-level annotations. Specifically, we first change the traditional output channel from one to the number of categories to achieve multiclass counting. Since all categories of objects use the same feature extractor in our proposed framework, their features will interfere mutually in the shared feature space. We further design a multi-mask structure to suppress harmful interaction among objects. Extensive experiments on the challenging benchmarks illustrate that the proposed method achieves state-of-the-art counting performance.