SeqCount: A sequence modeling framework for class-agnostic counting

Class-agnostic counting aims to count the number of objects in any category with only a few exemplars. It is crucial for solving the challenge of counting any visual class without re-finetuning, which in turn lowers deployment costs across diverse scenarios. Existing methods count the number of exemplar objects by integrating them over the density map smoothed by Gaussian kernels. However, designing generic kernels to generate density maps is challenging due to the different sizes and shapes of objects. To solve this problem, we propose SeqCount, which eliminates the need for density maps and treats object counting as a sequence generation problem. Specifically, we consider an input image as $N\times N$ patches and propose a serialization scheme. Then, we use an encoding-decoding structure to exploit the correlation among the patches. Experimental results on five challenging datasets demonstrate that our method performs favorably against the state-of-the-art models.