Search Results for author:
Found 2 papers, 0 papers with code
Cross Domain Adaptation using Adversarial networks with Cyclic loss
Deep Learning methods are highly local and sensitive to the domain of data they are trained with.
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
Cannot find the paper you are looking for? You can
Submit a new open access paper.
