DNN Optimization

Title	Year	Type	Tag	Blog
Learning both Weights and Connections for Efficient Neural Networks	2015	NIPS	pruning	blog
Deep Compression : Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding	2016	ICLR	pruning, quantization	blog
8-bit Inference with TensorRT	2017	GTC	quantization	Blog
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size	2016	-	Networks	blog
Sum-Product Networks: A New Deep Architecture	2011	UAI	SPN	-
Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1	2016	-	BNN	blog
Ternary weight networks	2016	-	BNN, TWNs	blog
ResNeSt	2020
ResNext	2017
SENet	2017
SKNet	2019
FReLU	2017
RepVGG	2021
ShuffleNet
An Ultra Lightweight CNN for Low Resource Circuit Component Recognition
RetinaNet