AI Paper Atlas

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

Leveraging Hierarchical Feature Sharing for Efficient Dataset Condensation

Haizhong Zheng, Jiachen Sun, Shutong Wu, Bhavya Kailkhura, Zhuoqing Morley Mao, Chaowei Xiao, Atul Prakash

ECCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 4 citations (OpenAlex)

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
replace image container with HMN under the same gradient matching lossdata parameterization for dataset condensation · CIFAR10 10 IPCtest accuracy (%): 67.8 (LinBa) -> 73.7Improved
add over-budget condensation with double-end pruning of instance-level memories (ablation)HMN · CIFAR10 50 IPCtest accuracy (%): 75.4 -> 76.9Improved
prune easy examples only instead of double-end pruning (ablation)HMN · CIFAR10 1 IPCtest accuracy (%): 65.7 -> 65.3Hurt
add over-budget pruning versus in-budget condensation at 1 IPC (ablation)HMN · CIFAR10 1 IPCtest accuracy (%): 65.1 -> 65.7Improved
increase instance-level memory size (GIPC falls from 85 to 13) (ablation)HMN · CIFAR10 1 IPCtest accuracy (%): 65.1% -> 48.2%Hurt
prune 30% of instances in 1 IPC HMN (ablation)HMN · CIFAR10 1 IPCtest accuracy (%): 66.2% -> 62.2%Hurt
prune 30% of instances in 50 IPC HMN (ablation)HMN · CIFAR10 50 IPCtest accuracy (%): 76.7% -> 76.5%No clear effect
prune 10% highest-AUM images of HaBa-generated data (ablation)HaBa · CIFAR10 10 IPCtest accuracy (%): 69.5 -> 69.5No clear effect
replace cosine annealing with multi-step LR scheduler (ablation)HMN · CIFAR10test accuracy (%): 73.7 -> 73.4 (10 IPC)No clear effect
replace trajectory loss with gradient matching loss in HaBa and LinBa (ablation)HaBa/LinBa · CIFAR10 10 IPCtest accuracy (%): 69.9 -> 61.8 (HaBa)Hurt
use HMN condensed with ConvNet to train other architecturesHMN vs IDC · CIFAR10 1 IPC cross-architecture (VGG16)test accuracy (%): 28.7 -> 58.5Improved
use HMN with batch-based loss instead of HaBa with trajectory lossHMN · CIFAR10 50 IPC GPU memoryGPU memory: 48276M -> 10426MImproved

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