no code implementations • ICCV 2023 • Yunqiang Li, Jan C. van Gemert, Torsten Hoefler, Bert Moons, Evangelos Eleftheriou, Bram-Ernst Verhoef
Deep learning algorithms are increasingly employed at the edge.
1 code implementation • 4 Mar 2023 • Joris Quist, Yunqiang Li, Jan van Gemert
Our analysis makes it possible to understand how magnitude-based hyperparameters influence the training of binary networks which allows for new optimization filters specifically designed for binary neural networks that are independent of their real-valued interpretation.
1 code implementation • 2 Dec 2021 • Yunqiang Li, Silvia L. Pintea, Jan C. van Gemert
We investigate experimentally that equal bit ratios are indeed preferable and show that our method leads to optimization benefits.
no code implementations • 1 Jan 2021 • Yunqiang Li, Silvia Laura Pintea, Jan van Gemert
We make the observation that pruning weights adds the value 0 as an additional symbol and thus increases the information capacity of the network.
1 code implementation • 22 Dec 2020 • Yunqiang Li, Jan van Gemert
This layer is shown to minimize a penalized term of the Wasserstein distance between the learned continuous image features and the optimal half-half bit distribution.
no code implementations • 16 Oct 2020 • Xiangwei Shi, Seyran Khademi, Yunqiang Li, Jan van Gemert
Current weakly supervised object localization and segmentation rely on class-discriminative visualization techniques to generate pseudo-labels for pixel-level training.
no code implementations • 14 Oct 2020 • Xiangwei Shi, Yunqiang Li, Xin Liu, Jan van Gemert
Such methods are less stable than BN as they critically depend on the statistics of a single input sample.
no code implementations • 31 Aug 2019 • Yunqiang Li, Wenjie Pei, Yufei zha, Jan van Gemert
In this paper we push for quantization: We optimize maximum class separability in the binary space.