REVIEW 6 cited by
DANCE: Dual-View Distribution Alignment for Dataset Condensation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
DANCE: Dual-View Distribution Alignment for Dataset Condensation
read the original abstract
Dataset condensation addresses the problem of data burden by learning a small synthetic training set that preserves essential knowledge from the larger real training set. To date, the state-of-the-art (SOTA) results are often yielded by optimization-oriented methods, but their inefficiency hinders their application to realistic datasets. On the other hand, the Distribution-Matching (DM) methods show remarkable efficiency but sub-optimal results compared to optimization-oriented methods. In this paper, we reveal the limitations of current DM-based methods from the inner-class and inter-class views, i.e., Persistent Training and Distribution Shift. To address these problems, we propose a new DM-based method named Dual-view distribution AligNment for dataset CondEnsation (DANCE), which exploits a few pre-trained models to improve DM from both inner-class and inter-class views. Specifically, from the inner-class view, we construct multiple "middle encoders" to perform pseudo long-term distribution alignment, making the condensed set a good proxy of the real one during the whole training process; while from the inter-class view, we use the expert models to perform distribution calibration, ensuring the synthetic data remains in the real class region during condensing. Experiments demonstrate the proposed method achieves a SOTA performance while maintaining comparable efficiency with the original DM across various scenarios. Source codes are available at https://github.com/Hansong-Zhang/DANCE.
Forward citations
Cited by 6 Pith papers
-
Robust Trajectory Distillation: Hybrid Reweighting Meets Teacher-Inspired Targets
Introduces SGR and TIAT for robust dataset distillation that suppresses noise while preserving knowledge under noisy supervision.
-
Multimodal Distribution Matching for Vision-Language Dataset Distillation
MDM distills vision-language datasets via joint embedding clustering, weight-space model interpolation, and geometry-aware distribution matching on the unit hypersphere.
-
DIVER:Diving Deeper into Distilled Data via Expressive Semantic Recovery
DIVER is a dual-stage distillation method using diffusion models to enhance semantic preservation and cross-architecture generalization in dataset distillation.
-
Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation
DO-ALL uses dataset distillation to create synthetic source anchors that enable stable long-term continual test-time adaptation without storing original source data.
-
Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation
DO-ALL applies dataset distillation to generate synthetic source anchors that stabilize continual test-time adaptation under evolving domains without storing original source data.
-
DIVER:Diving Deeper into Distilled Data via Expressive Semantic Recovery
DIVER applies a pre-trained diffusion model in a dual-stage process of semantic inheritance, guidance, and fusion to improve semantic expression and cross-architecture generalization in dataset distillation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.