Finding Non-Uniform Quantization Schemes using Multi-Task Gaussian Processes
We propose a novel method for neural network quantization that casts the neural architecture search problem as one of hyperparameter search to find non-uniform bit distributions throughout the layers of a CNN. We perform the search assuming a Multi-Task Gaussian Processes prior, which splits the problem to multiple tasks, each corresponding to different number of training epochs, and explore the space by sampling those configurations that yield maximum information. We then show that with significantly lower precision in the last layers we achieve a minimal loss of accuracy with appreciable memory savings. We test our findings on the CIFAR10 and ImageNet datasets using the VGG, ResNet and GoogLeNet architectures.
PDF Abstract ECCV 2020 PDF ECCV 2020 Abstract
Datasets
Add Datasets
introduced or used in this paper
Results from the Paper
Submit
results from this paper
to get state-of-the-art GitHub badges and help the
community compare results to other papers.
Methods
1x1 Convolution •
Auxiliary Classifier •
Average Pooling •
Batch Normalization •
Bottleneck Residual Block •
Convolution •
Dense Connections •
Dropout •
Global Average Pooling •
GoogLeNet •
Inception Module •
Kaiming Initialization •
Local Response Normalization •
Max Pooling •
ReLU •
Residual Block •
Residual Connection •
ResNet •
Softmax •
VGG
