High Performance Binarized Neural Networks trained on the ImageNet Classification Task

10 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Model compression via distillation and quantization (2018, methodology): “The first direction is the work on training quantized neural networks, e.g. Courbariaux et al. (2015); Rastegari et al. (2016); Hubara et al. (2016); Wu et al. (2016a); Mellempudi et al. (2017); Ott et al. (2016); Zhu et al. (2016), which showed that neural networks can converge to good task…”
Inducing and Exploiting Activation Sparsity for Fast Neural Network Inference (2020, background): “Our work can also be examined in the broader context of model compression methods, which is an extremely active research area, e.g. (Wu et al., 2016; Zhu et al., 2016; Mishra et al., 2017; Mellempudi et al., 2017; Zhang et al., 2017; Park et al., 2016b; Han et al., 2016; Polino et al., 2018;…”
How to Train a Compact Binary Neural Network with High Accuracy? (2017, background): “It should be noted that adding a scale layer after the binarized last layer has also been adopted by (Wu 2016), but this strategy is not the only factor for achieving high compression rate in our binary network, which will be further demonstrated in Section 4.”