most citedLSQ+: Improving low-bit quantization through learnable offsets and better initialization

17 citations · 42 across the 3 of their papers we have counts for

collaborators

7 papers

cs.CV202017 cited

LSQ+: Improving low-bit quantization through learnable offsets and better initialization

Yash Bhalgat, Jinwon Lee, Markus Nagel +2

Unlike ReLU, newer activation functions (like Swish, H-swish, Mish) that are frequently employed in popular efficient architectures can also result in negative activation values, w…

cs.LG2020

Up or Down? Adaptive Rounding for Post-Training Quantization

Markus Nagel, Rana Ali Amjad, Mart van Baalen +2

When quantizing neural networks, assigning each floating-point weight to its nearest fixed-point value is the predominant approach. We find that, perhaps surprisingly, this is not…

cs.CV2020

Conditional Channel Gated Networks for Task-Aware Continual Learning

Davide Abati, Jakub Tomczak, Tijmen Blankevoort +3

Convolutional Neural Networks experience catastrophic forgetting when optimized on a sequence of learning problems: as they meet the objective of the current training examples, the…

cs.LG202010 cited

Gradient Regularization for Quantization Robustness

Milad Alizadeh, Arash Behboodi, Mart van Baalen +3

We analyze the effect of quantizing weights and activations of neural networks on their loss and derive a simple regularization scheme that improves robustness against post-trainin…

cs.LG201915 cited

Taxonomy and Evaluation of Structured Compression of Convolutional Neural Networks

Andrey Kuzmin, Markus Nagel, Saurabh Pitre +3

The success of deep neural networks in many real-world applications is leading to new challenges in building more efficient architectures. One effective way of making networks more…

cs.LG2019

Batch-Shaping for Learning Conditional Channel Gated Networks

Babak Ehteshami Bejnordi, Tijmen Blankevoort, Max Welling

We present a method that trains large capacity neural networks with significantly improved accuracy and lower dynamic computational cost. We achieve this by gating the deep-learnin…