Search Results for author:
Found 2 papers, 0 papers with code
R2 Loss: Range Restriction Loss for Model Compression and Quantization
To overcome the challenge, we focus on outliers in weights of a pre-trained model which disrupt effective lower bit quantization and compression.
Ranked #1 on
Model Compression
on QNLI
SNOW: Subscribing to Knowledge via Channel Pooling for Transfer & Lifelong Learning of Convolutional Neural Networks
SNOW is an efficient learning method to improve training/serving throughput as well as accuracy for transfer and lifelong learning of convolutional neural networks based on knowledge subscription.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
