AI Paper Atlas

Research map / Benchmarks / ImageNet-1K IPC=10

ImageNet-1K IPC=10 leaderboard

30 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ImageNet-1K IPC=10. Best accuracy: 58.1 (FADRM+, NeurIPS 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

ImageNet-1K IPC=10 · accuracy

30 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
158.1FADRM+
ResNet101
FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation
NeurIPS 2025 · Main results table
RNNs and normalization
256.3Proposed
ResNet-101
An Adaptive Sampling Framework for Diffusion-based Dataset Distillation with High Fidelity and Diversity
AAAI 2026 · Table 2
Fast diffusion sampling
354.3CIM
ResNet-50
Condensing Large-Scale Datasets Directly with Minimal Information Loss
ECCV 2026 · Table 3
Pruning and efficient tuning
453.2RETA
ResNet-18 (trained from scratch on distilled data)
Fixed Anchors Are Not Enough: Dynamic Retrieval and Persistent Homology for Dataset Distillation
CVPR 2026 · Table 1
Knowledge distillation
552.4BPS
ResNet-18
Balanced Dataset Distillation via Modeling Multiple Visual Pattern Distribution
CVPR 2026 · Table 1
Recognition and long-tail
651.4InfoUtil
ResNet-101 student
Grounding and Enhancing Informativeness and Utility in Dataset Distillation
ICLR 2026 · Table 1
Knowledge distillation
750.4UniDD
ResNet-18
Towards Universal Dataset Distillation via Task-Driven Diffusion
CVPR 2025 · Table 1
Fast diffusion sampling
850.01Grid-Distil (Detail Enhancement)
ResNet-18
Grid Distillation: Compositional Image Distillation via Structured Generative Grids
CVPR 2026 · Table 4
Fast diffusion sampling
948.6EDC
ResNet-18
Elucidating the Design Space of Dataset Condensation
NeurIPS 2024 · Table (ResNet-18 results)
RNNs and normalization
1047.6HierAmp
ResNet-18 student
HierAmp: Coarse-to-Fine Autoregressive Amplification for Generative Dataset Distillation
CVPR 2026 · Table 1
CNN features
20 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.