object counting, Refinement Network (RefNet), scale variation, uneven distribution
To address the scale variance and uneven distribution of objects in scenarios of object-counting tasks, an algorithm called Refinement Network (RefNet) is exploited. The proposed top-down scheme sequentially aggregates multiscale features, which are laterally connected with low-level information. Trained by a multiresolution density regression loss, a set of intermediate-density maps are estimated on each scale in a multiscale feature pyramid, and the detailed information of the density map is gradually added through coarse-to-fine granular refinement progress to predict the final density map. We evaluate our RefNet on three crowd-counting benchmark datasets, namely, ShanghaiTech, UCF_CC_50, and UCSD, and our method achieves competitive performances on the mean absolute error and root mean squared error compared to the state-of-the-art approaches. We further extend our RefNet to cell counting, illustrating its effectiveness on relative counting tasks.
Sun, Lehan; Ma, Junjie; and Jing, Liping
"Object Counting Using a Refinement Network,"
Tsinghua Science and Technology: Vol. 27:
5, Article 9.
Available at: https://dc.tsinghuajournals.com/tsinghua-science-and-technology/vol27/iss5/9