Research
DeCO: Discriminative Evidence Composition for Fine-Grained Dataset Distillation
arXiv:2608.25480v1 Announce Type: new Abstract: Dataset distillation compresses a large training set into a compact synthetic set while preserving its downstream utility. However, existing methods pri
arXiv:2608.25480v1 Announce Type: new 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.
Related
- Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust?
- Spectral Gradient Surgery for Domain-Generalizable Dataset Distillation
- FD^2: A Dedicated Framework for Fine-Grained Dataset Distillation
- Self-Supervised Representation-Guided Generative Dataset Distillation
Source: arXiv cs.CV | 2026-08-27