Training Competitive Binary Neural Networks from Scratch
This enables more efficient deployment of neural networks on mobile and embedded devices with low computational power, representing a strong specific gain rather than an incremental improvement.
The paper tackles the challenge of training accurate binary neural networks from scratch without using prior knowledge from full-precision models, achieving state-of-the-art results on standard benchmark datasets and further improving performance by successfully adopting dense connections in binary networks.
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.