no code implementations • 7 Jul 2022 • Lusine Abrahamyan, Nikos Deligiannis
Patches with high entropy are being processed by the encoder with the largest number of parameters, patches with moderate entropy are processed by the encoder with a moderate number of parameters, and patches with low entropy are processed by the smallest encoder.
1 code implementation • 2 Feb 2022 • Lusine Abrahamyan, Anh Minh Truong, Wilfried Philips, Nikos Deligiannis
Further, we minimize the distance between the computed variance maps to enforce the model to produce high variance gradient maps that will lead to the generation of high-resolution images with sharper edges.
2 code implementations • ICCV 2021 • Lusine Abrahamyan, Valentin Ziatchin, Yiming Chen, Nikos Deligiannis
In compact CNNs, due to the limited number of parameters, abundant features are unlikely to be obtained, and feature diversity becomes an essential characteristic.
Ranked #816 on Image Classification on ImageNet
no code implementations • 16 Mar 2021 • Lusine Abrahamyan, Yiming Chen, Giannis Bekoulis, Nikos Deligiannis
In contrast, we advocate that the gradients across the nodes are correlated and propose methods to leverage this inter-node redundancy to improve compression efficiency.