-
Part VI: combining compressions
Model compression is generally performed by using quantization, low-rank approximation or pruning, for which various algorithms have been researched in recent years. -
Low-rank compression of neural nets: Learning the rank of each layer
Model compression is generally performed by using quantization, low-rank approximation or pruning, for which various algorithms have been researched in recent years. -
Part V: combining compressions
Model compression is generally performed by using quantization, low-rank approximation or pruning, for which various algorithms have been researched in recent years. -
Model compression as constrained optimization
Model compression is generally performed by using quantization, low-rank approximation or pruning, for which various algorithms have been researched in recent years. -
ExplainFix: Explainable Spatially Fixed Deep Networks
ExplainFix adopts two design principles: the “fixed filters” principle that all spatial filter weights of convolutional neural networks can be fixed at initialization and never... -
Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation
Joint-DetNAS is a unified framework for object detection that jointly optimizes NAS, pruning, and dynamic distillation.
