Search Results for author:
Found 8 papers, 5 papers with code
REPrune: Filter Pruning via Representative Election
Even though norm-based filter pruning methods are widely accepted, it is questionable whether the "smaller-norm-less-important" criterion is optimal in determining filters to prune.
Neuron Merging: Compensating for Pruned Neurons
Network pruning is widely used to lighten and accelerate neural network models.
DepthFL: Depthwise Federated Learning for Heterogeneous Clients
Federated learning is for training a global model without collecting private local data from clients.
NaturalInversion: Data-Free Image Synthesis Improving Real-World Consistency
We introduce NaturalInversion, a novel model inversion-based method to synthesize images that agrees well with the original data distribution without using real data.
GuidedMixup: An Efficient Mixup Strategy Guided by Saliency Maps
From this motivation, we propose a novel saliency-aware mixup method, GuidedMixup, which aims to retain the salient regions in mixup images with low computational overhead.
Probabilistic Precision and Recall Towards Reliable Evaluation of Generative Models
Assessing the fidelity and diversity of the generative model is a difficult but important issue for technological advancement.
Catch-Up Mix: Catch-Up Class for Struggling Filters in CNN
Deep learning has made significant advances in computer vision, particularly in image classification tasks.
REPrune: Channel Pruning via Kernel Representative Selection
Channel pruning is widely accepted to accelerate modern convolutional neural networks (CNNs).
