no code implementations • 17 Sep 2019 • Zhi-Qi Cheng, Jun-Xiu Li, Qi Dai, Xiao Wu, Jun-Yan He, Alexander Hauptmann
By minimizing the mutual information, each column is guided to learn features with different image scales.
no code implementations • ICCV 2019 • Zhi-Qi Cheng, Jun-Xiu Li, Qi Dai, Xiao Wu, Alexander Hauptmann
Although the Maximum Excess over SubArrays (MESA) loss has been previously proposed to address the above issues by finding the rectangular subregion whose predicted density map has the maximum difference from the ground truth, it cannot be solved by gradient descent, thus can hardly be integrated into the deep learning framework.
Ranked #5 on Crowd Counting on WorldExpo’10