AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

FD²: A Dedicated Framework for Fine-Grained Dataset Distillation

Hongxu Ma, Guang Li, Shijie Wang, DONGZHAN ZHOU, Baoli Sun, Takahiro Ogawa, Miki Haseyama, Zhihui Wang

ECCV 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias

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 changedWhereMeasuredEffect
add fine-grained characteristic constraint (ablation)SRe2L++ · CUB-200-2011 IPC=3 ResNet18Top-1 accuracy: 63.4 -> 64.8Improved
add similarity constraint (ablation)SRe2L++ · CUB-200-2011 IPC=3 ResNet18Top-1 accuracy: 63.4 -> 64.6Improved
add both constraints together (ablation)SRe2L++ · CUB-200-2011 IPC=3 ResNet18Top-1 accuracy: 63.4 -> 64.9Improved
increase group size N_S from 4 to 5 in similarity constraint (ablation)SRe2L++_FD2 · CUB-200-2011 IPC=5Top-1 accuracy: 66.1 -> 64.6Hurt
set beta to 0.5 instead of 0 in fine-grained constraint (ablation)SRe2L++_FD2 · CUB-200-2011 IPC=3Top-1 accuracy: 63.5 -> 64.8Improved
set CAL ratio alpha to 0.5 instead of 0.7 (ablation)SRe2L++_FD2 · CUB-200-2011 IPC=3Top-1 accuracy: 62.1 -> 63.4Improved
set constraint weight lambda to 0.8 instead of 0.2SRe2L++_FD2 · CUB-200-2011Top-1 accuracy: 65.4 -> 67.0Improved
integrate FD2 into FADRM+FADRM+ · Stanford Cars ResNet18 IPC=1Top-1 accuracy: 60.3 -> 74.1Improved
integrate FD2 into FADRM+FADRM+ · CUB-200-2011 ResNet50 IPC=3Top-1 accuracy: 70.4 -> 70.6No clear effect
integrate FD2 into FADRM+ with small studentFADRM+ · ImageNette ResNet18 IPC=1Top-1 accuracy: 39.2 -> 38.6Hurt
integrate FD2 into FADRM+ with larger studentFADRM+ · ImageNette ResNet50 IPC=1Top-1 accuracy: 31.9 -> 39.0Improved
integrate FD2 into FADRM+FADRM+ · ImageWoof ResNet50 IPC=1Top-1 accuracy: 19.9 -> 30.3Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy