EfficientDNNs

A collection of recent methods on DNN compression and acceleration. There are mainly 5 kinds of methods for efficient DNNs:

neural architecture re-designing or searching
- maintain accuracy, less cost (e.g., #Params, #FLOPs, etc.): MobileNet, ShuffleNet etc.
- maintain cost, more accuracy: Inception, ResNeXt, Xception etc.
pruning (including structured and unstructured)
quantization
matrix decomposition
knowledge distillation

About abbreviation: In the list below, o for oral, w for workshop, s for spotlight, b for best paper.

Papers