Data-efficient Neural Network Training with Dataset Condensation

Bo Zhao

The University of Edinburgh 2023 · first public 2023-01

paper ↗catalogued✓ metadata verified

In one paragraph

PhD thesis presenting the author's own gradient-matching (DC), differentiable-Siamese-augmentation (DSA) and distribution-matching (DM) approaches to dataset condensation as one body of work on data-efficient neural network training.

Where it sits

Gradient matching (Surrogate matching)
Distribution and feature matching (Surrogate matching)
Setting: Image classification

Builds on

BibTeX (generated; prefer the venue's official entry)

@article{zhao2023data,
  title   = {Data-efficient Neural Network Training with Dataset Condensation},
  author  = {Bo Zhao},
  journal = {The University of Edinburgh 2023},
  year    = {2023}
}

Nearby in Gradient matching

2025-11

Linear Gradient Matching — Dataset Distillation for Pre-Trained Self-Supervised Vision Models

George Cazenavette, Antonio Torralba, Vincent Sitzmann · NeurIPS 2025notablePre-training & transfer paper ↗code ↗

2025-05

PRISM — PRISM: Video Dataset Condensation with Progressive Refinement and Insertion for Sparse Motion

Jaehyun Choi, Jiwan Hur, Gyojin Han et al. · CVPR 2026notableVideo paper ↗

2025-02

GRADMM — Synthetic Text Generation for Training Large Language Models via Gradient Matching

Dang Nguyen, Zeman Li, Mohammadhossein Bateni et al. · ICML 2025notableText paper ↗code ↗

2024-04

Distilled Datamodel with Reverse Gradient Matching

Jingwen Ye, Ruonan Yu, Songhua Liu et al. · CVPR 2024notablepaper ↗

2023-12

Static-dynamic video DD — Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement

Ziyu Wang, Yue Xu, Cewu Lu et al. · CVPR 2024coreVideo paper ↗code ↗