Search Results for author:
Found 6 papers, 5 papers with code
Self-supervised Dataset Distillation: A Good Compression Is All You Need
In this work, we consider addressing this task through the new lens of model informativeness in the compression stage on the original dataset pretraining.
Dataset Distillation in Large Data Era
Dataset distillation aims to generate a smaller but representative subset from a large dataset, which allows a model to be trained efficiently, meanwhile evaluating on the original testing data distribution to achieve decent performance.
Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching
We call this perspective "generalized matching" and propose Generalized Various Backbone and Statistical Matching (G-VBSM) in this work, which aims to create a synthetic dataset with densities, ensuring consistency with the complete dataset across various backbones, layers, and statistics.
Rethinking Mixup for Improving the Adversarial Transferability
In this work, we posit that the adversarial examples located at the convergence of decision boundaries across various categories exhibit better transferability and identify that Admix tends to steer the adversarial examples towards such regions.
Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective
The proposed method demonstrates flexibility across diverse dataset scales and exhibits multiple advantages in terms of arbitrary resolutions of synthesized images, low training cost and memory consumption with high-resolution synthesis, and the ability to scale up to arbitrary evaluation network architectures.
Backdoor Attacks on Federated Learning with Lottery Ticket Hypothesis
Edge devices in federated learning usually have much more limited computation and communication resources compared to servers in a data center.
