DeCO: Discriminative Evidence Composition for Fine-Grained Dataset Distillation

2026-08-26

AI Summary

本文提出DeCO方法，通过保留区分性证据解决细粒度数据集蒸馏中忽略局部特征的问题，实验表明其在不同预算下优于现有方法。

Abstract

Dataset distillation compresses a large training set into a compact synthetic set while preserving its downstream utility. However, existing methods primarily preserve global image statistics and may overlook the localized evidence essential for fine-grained visual classification (FGVC), such as object parts, subtle textures, and region-specific structures. We formulate fine-grained dataset distillation as budgeted discriminative-evidence preservation and propose Discriminative Evidence Composition (DeCO). DeCO uses attention rollout from a pretrained TransFG teacher to identify informative patches, applies spatial diversification to reduce redundant coverage, and organizes the resulting regions into class-wise evidence banks. Multiple same-class regions are then packed into compact grid-composed images. The teacher is used only for dataset construction, whereas downstream students are trained with standard hard-label supervision without teacher logits. Experiments on CUB-200-2011, FGVC-Aircraft, and Stanford Cars show that DeCO consistently outperforms representative coreset and dataset-distillation baselines under different IPC budgets.

Problem

• dataset distillation
• fine-grained visual classification
• local evidence

Innovation

• Discriminative Evidence Composition
• Fine-Grained Visual Classification
• Attention Rollout
• Spatial Diversification
• Dataset Distillation