Pith. sign in

REVIEW 2 cited by

Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarios

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.17193 v2 pith:PRELMHPM submitted 2024-10-22 cs.CV cs.AI

Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarios

classification cs.CV cs.AI
keywords complexscenariosdatasetdistillationareasdiscriminativeactivationbenchmark
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Dataset distillation has demonstrated strong performance on simple datasets like CIFAR, MNIST, and TinyImageNet but struggles to achieve similar results in more complex scenarios. In this paper, we propose EDF (emphasizes the discriminative features), a dataset distillation method that enhances key discriminative regions in synthetic images using Grad-CAM activation maps. Our approach is inspired by a key observation: in simple datasets, high-activation areas typically occupy most of the image, whereas in complex scenarios, the size of these areas is much smaller. Unlike previous methods that treat all pixels equally when synthesizing images, EDF uses Grad-CAM activation maps to enhance high-activation areas. From a supervision perspective, we downplay supervision signals that have lower losses, as they contain common patterns. Additionally, to help the DD community better explore complex scenarios, we build the Complex Dataset Distillation (Comp-DD) benchmark by meticulously selecting sixteen subsets, eight easy and eight hard, from ImageNet-1K. In particular, EDF consistently outperforms SOTA results in complex scenarios, such as ImageNet-1K subsets. Hopefully, more researchers will be inspired and encouraged to improve the practicality and efficacy of DD. Our code and benchmark will be made public at https://github.com/NUS-HPC-AI-Lab/EDF.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Federated Distillation for Whole Slide Image via Gaussian-Mixture Feature Alignment and Curriculum Integration

    cs.CV 2026-05 unverdicted novelty 5.0

    FedHD performs federated distillation for whole slide images by generating one synthetic feature set per real slide via Gaussian-mixture alignment and adding them via curriculum integration, outperforming prior federa...

  2. Federated Distillation for Whole Slide Image via Gaussian-Mixture Feature Alignment and Curriculum Integration

    cs.CV 2026-05 unverdicted novelty 5.0

    FedHD is a federated learning framework for whole slide images that distills one-to-one synthetic features aligned via Gaussian mixtures and progressively integrates cross-site features through curriculum learning to ...