Training a ResNet-18 with smoothness penalties on weights, then compressing via truncated SVD, keeps 91% CIFAR-10 accuracy at 70% sparsity with no post-compression fine-tuning.
Depthwise Separable Convolutions Allow for Fast and Memory-Efficient Spectral Normalization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
An increasing number of models require the control of the spectral norm of convolutional layers of a neural network. While there is an abundance of methods for estimating and enforcing upper bounds on those during training, they are typically costly in either memory or time. In this work, we introduce a very simple method for spectral normalization of depthwise separable convolutions, which introduces negligible computational and memory overhead. We demonstrate the effectiveness of our method on image classification tasks using standard architectures like MobileNetV2.
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Smooth Model Compression without Fine-Tuning
Training a ResNet-18 with smoothness penalties on weights, then compressing via truncated SVD, keeps 91% CIFAR-10 accuracy at 70% sparsity with no post-compression fine-tuning.