Dataset Distillation with Convexified Implicit Gradients
We propose a new dataset distillation algorithm using reparameterization and convexification of implicit gradients (RCIG), that substantially improves the state-of-the-art. To this end, we first formulate dataset distillation as a bi-level optimization problem. Then, we show how implicit gradients can be effectively used to compute meta-gradient updates. We further equip the algorithm with a convexified approximation that corresponds to learning on top of a frozen finite-width neural tangent kernel. Finally, we improve bias in implicit gradients by parameterizing the neural network to enable analytical computation of final-layer parameters given the body parameters. RCIG establishes the new state-of-the-art on a diverse series of dataset distillation tasks. Notably, with one image per class, on resized ImageNet, RCIG sees on average a 108\% improvement over the previous state-of-the-art distillation algorithm. Similarly, we observed a 66\% gain over SOTA on Tiny-ImageNet and 37\% on CIFAR-100.
Code (2)
Tasks
Dataset DistillationDataset Distillation - 1IPCSimilar Papers 제목 키워드 기반
Towards Stable and Storage-efficient Dataset Distillation: Matching Convexified Trajectory
The rapid evolution of deep learning and large language models has led to an exponential growth in the demand for training data, prompting the development of Dataset Distillation methods to address the challenges of mana…
Dataset DistillationDreamHOI: Subject-Driven Generation of 3D Human-Object Interactions with Diffusion Priors
We present DreamHOI, a novel method for zero-shot synthesis of human-object interactions (HOIs), enabling a 3D human model to realistically interact with any given object based on a textual description. This task is comp…
Human-Object Interaction DetectionNeRFGuiding Distribution Matching Distillation with Gradient-Based Reinforcement Learning
Diffusion distillation, exemplified by Distribution Matching Distillation (DMD), has shown great promise in few-step generation but often sacrifices quality for sampling speed. While integrating Reinforcement Learning (R…
Reinforcement LearningConvexified Convolutional Neural Networks
We describe the class of convexified convolutional neural networks (CCNNs), which capture the parameter sharing of convolutional neural networks in a convex manner. By representing the nonlinear convolutional filters as …
DenoisingUnderstanding the Role of the Projector in Knowledge Distillation
In this paper we revisit the efficacy of knowledge distillation as a function matching and metric learning problem. In doing so we verify three important design decisions, namely the normalisation, soft maximum function,…
image-classificationImage ClassificationKnowledge DistillationMetric Learning+2