GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost

TL;DR

This paper introduces GIFT, a simple yet effective method to fully utilize labels in dataset distillation, significantly improving performance and generalization across datasets without extra costs.

Contribution

GIFT provides a universal loss function and label refinement technique that enhances dataset distillation effectiveness and cross-optimizer generalization.

Findings

GIFT improves state-of-the-art results across datasets.

GIFT enhances cross-optimizer generalization notably.

GIFT achieves significant performance gains on ImageNet-1K.

Abstract

Recent advancements in dataset distillation have demonstrated the significant benefits of employing soft labels generated by pre-trained teacher models. In this paper, we introduce a novel perspective by emphasizing the full utilization of labels. We first conduct a comprehensive comparison of various loss functions for soft label utilization in dataset distillation, revealing that the model trained on the synthetic dataset exhibits high sensitivity to the choice of loss function for soft label utilization. This finding highlights the necessity of a universal loss function for training models on synthetic datasets. Building on these insights, we introduce an extremely simple yet surprisingly effective plug-and-play approach, GIFT, which encompasses soft label refinement and a cosine similarity-based loss function to efficiently leverage full label information. Extensive experiments indicate that GIFT consistently enhances state-of-the-art dataset distillation methods across various dataset scales, without incurring additional computational costs. Importantly, GIFT significantly enhances cross-optimizer generalization, an area previously overlooked. For instance, on ImageNet-1K with IPC = 10, GIFT enhances the state-of-the-art method RDED by 30.8% in cross-optimizer generalization. Our code is available at https://github.com/LINs-lab/GIFT.