.png){kind=icon}
.png){kind=icon}
Return
Object Counting Using a Refinement Network
.png){kind=icon}
OA
AI
DOI：10.26599/TST.2021.9010097.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
Aggregates
Semantics
Estimation
Benchmark testing
Decoding
Noise measurement
Background noise
object counting
Refinement Network (RefNet)
scale variation
uneven distribution
Journal
T
IF:
3.5
Papers:
987
Citations:
2.5K