T
Tijmen Blankevoort
Researcher at Qualcomm
Publications - 41
Citations - 1295
Tijmen Blankevoort is an academic researcher from Qualcomm. The author has contributed to research in topics: Quantization (signal processing) & Computer science. The author has an hindex of 12, co-authored 27 publications receiving 571 citations.
Papers
More filters
Proceedings ArticleDOI
Data-Free Quantization Through Weight Equalization and Bias Correction
TL;DR: This work introduces a data-free quantization method for deep neural networks that does not require fine-tuning or hyperparameter selection, and achieves near-original model performance on common computer vision architectures and tasks.
Posted Content
Up or Down? Adaptive Rounding for Post-Training Quantization
TL;DR: AdaRound is proposed, a better weight-rounding mechanism for post-training quantization that adapts to the data and the task loss that outperforms rounding-to-nearest by a significant margin and establishes a new state-of-the-art forPost- training quantization on several networks and tasks.
Proceedings ArticleDOI
Conditional Channel Gated Networks for Task-Aware Continual Learning
Davide Abati,Jakub M. Tomczak,Tijmen Blankevoort,Simone Calderara,Rita Cucchiara,Babak Ehteshami Bejnordi +5 more
TL;DR: In this article, task-specific gating modules are used to select which filters to apply on the given input, ensuring no loss in the performance of the model for previously learned tasks.
Proceedings ArticleDOI
LSQ+: Improving low-bit quantization through learnable offsets and better initialization
TL;DR: LSQ+ is the first work to quantize such architectures to extremely low bit-widths and shows state-of-the-art results for EfficientNet and MixNet and also significantly outperforms LSQ for low-bit quantization of neural nets with Swish activations.
Proceedings Article
Relaxed Quantization for Discretized Neural Networks
TL;DR: It is shown that stochastic rounding can be seen as a special case of the proposed approach and that under this formulation the quantization grid itself can also be optimized with gradient descent.