Research map / Label-efficient and robust learning / Knowledge distillation
Sequential Subset Matching for Dataset Distillation
Jiawei Du, Qin Shi, Joey Tianyi Zhou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| plug SeqMatch into MTT | MTT · CIFAR-100 ipc=50 | test accuracy (%): 47.7 -> 51.2 | Improved |
| plug SeqMatch into MTT | MTT · CIFAR-10 ipc=50 | test accuracy (%): 71.6 -> 74.4 | Improved |
| plug SeqMatch into MTT | MTT · CIFAR-10 ipc=10 | test accuracy (%): 65.3 -> 66.2 | Improved |
| plug SeqMatch into MTT | MTT · Tiny ImageNet ipc=10 | test accuracy (%): 23.2 -> 23.8 | Improved |
| plug SeqMatch into IDC | IDC · SVHN ipc=50 | test accuracy (%): 90.2 -> 92.1 | Improved |
| plug SeqMatch into IDC | IDC · SVHN ipc=10 | test accuracy (%): 87.3 -> 87.2 | No clear effect |
| plug SeqMatch into IDC | IDC · CIFAR-10 ipc=50 | test accuracy (%): 74.5 -> 75.3 | Improved |
| plug SeqMatch into MTT | MTT · MNIST ipc=50 | test accuracy (%): 98.5 -> 99.0 | Improved |
| evaluate SeqMatch-MTT on other architectures | MTT · CIFAR-10 ipc=50, ResNet18 | test accuracy (%): 61.9 -> 68.4 | Improved |
| evaluate SeqMatch-MTT on other architectures | MTT · CIFAR-10 ipc=50, VGG11 | test accuracy (%): 55.4 -> 64.2 | Improved |
| evaluate SeqMatch-MTT on other architectures | MTT · CIFAR-10 ipc=50, AlexNet | test accuracy (%): 48.2 -> 50.7 | Improved |
| plug SeqMatch into MTT | MTT · ImageNette ipc=10 | test accuracy (%): 63.0 -> 66.9 | Improved |
Closest papers by meaning
- Large Scale Dataset Distillation with Domain Shift (ICML 2024 · similarity 0.89)
- Embarrassingly Simple Dataset Distillation (ICLR 2024 · similarity 0.89)
- Distilling Long-tailed Datasets (CVPR 2025 · similarity 0.89)
- Dataset Distillation for Pre-Trained Self-Supervised Vision Models (NeurIPS 2025 · similarity 0.88)
- Boost Self-Supervised Dataset Distillation via Parameterization, Predefined Augmentation, and Approximation (ICLR 2025 · similarity 0.88)
- Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality (ICLR 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
