Search Results for author:
Found 7 papers, 4 papers with code
Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching
The ultimate goal of Dataset Distillation is to synthesize a small synthetic dataset such that a model trained on this synthetic set will perform equally well as a model trained on the full, real dataset.
Generalizing Dataset Distillation via Deep Generative Prior
Dataset Distillation aims to distill an entire dataset's knowledge into a few synthetic images.
Dataset Distillation by Matching Training Trajectories
To efficiently obtain the initial and target network parameters for large-scale datasets, we pre-compute and store training trajectories of expert networks trained on the real dataset.
MixerGAN: An MLP-Based Architecture for Unpaired Image-to-Image Translation
While attention-based transformer networks achieve unparalleled success in nearly all language tasks, the large number of tokens (pixels) found in images coupled with the quadratic activation memory usage makes them prohibitive for problems in computer vision.
On the Bias Against Inductive Biases
Borrowing from the transformer models that revolutionized the field of natural language processing, self-supervised feature learning for visual tasks has also seen state-of-the-art success using these extremely deep, isotropic networks.
Reframing Neural Networks: Deep Structure in Overcomplete Representations
In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark.
Architectural Adversarial Robustness: The Case for Deep Pursuit
Despite their unmatched performance, deep neural networks remain susceptible to targeted attacks by nearly imperceptible levels of adversarial noise.
