Two-stage and gradually decreasing quantization, stochastic precision sampling, and joint teacher-student distillation each improve low-bit CNN accuracy on ImageNet and CIFAR-100, with the largest gains when combined.
Training Competitive Binary Neural Networks from Scratch
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Convolutional neural networks have achieved astonishing results in different application areas. Various methods that allow us to use these models on mobile and embedded devices have been proposed. Especially binary neural networks are a promising approach for devices with low computational power. However, training accurate binary models from scratch remains a challenge. Previous work often uses prior knowledge from full-precision models and complex training strategies. In our work, we focus on increasing the performance of binary neural networks without such prior knowledge and a much simpler training strategy. In our experiments we show that we are able to achieve state-of-the-art results on standard benchmark datasets. Further, to the best of our knowledge, we are the first to successfully adopt a network architecture with dense connections for binary networks, which lets us improve the state-of-the-art even further.
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activations
Two-stage and gradually decreasing quantization, stochastic precision sampling, and joint teacher-student distillation each improve low-bit CNN accuracy on ImageNet and CIFAR-100, with the largest gains when combined.