CIM directly aligns data distributions to condense large-scale datasets with minimal information loss, achieving new SOTA results on ImageNet-1K distillation at IPC=10.
arXiv preprint arXiv:2310.05773 , year=
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
fields
cs.CV 7years
2026 7verdicts
UNVERDICTED 7representative citing papers
DMGD achieves better performance than fine-tuned SOTA methods in dataset distillation on ImageNet subsets by using semantic matching through conditional likelihood optimization and OT-based distribution matching in a training-free diffusion setup.
A replay method for continual face forgery detection condenses real-fake distribution discrepancies into compact maps and synthesizes compatible samples from current real faces to reduce forgetting under tight memory budgets without storing historical images.
Introduces SGR and TIAT for robust dataset distillation that suppresses noise while preserving knowledge under noisy supervision.
RAHA applies rank-aware hyperbolic alignment to vision-language dataset distillation by enforcing geodesic alignment in the shared low-rank range and regularizing the residual subspace for improved transfer.
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 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.
citing papers explorer
-
Condensing Large-Scale Datasets Directly with Minimal Information Loss
CIM directly aligns data distributions to condense large-scale datasets with minimal information loss, achieving new SOTA results on ImageNet-1K distillation at IPC=10.
-
DMGD: Train-Free Dataset Distillation with Semantic-Distribution Matching in Diffusion Models
DMGD achieves better performance than fine-tuned SOTA methods in dataset distillation on ImageNet subsets by using semantic matching through conditional likelihood optimization and OT-based distribution matching in a training-free diffusion setup.
-
Direct Discrepancy Replay: Distribution-Discrepancy Condensation and Manifold-Consistent Replay for Continual Face Forgery Detection
A replay method for continual face forgery detection condenses real-fake distribution discrepancies into compact maps and synthesizes compatible samples from current real faces to reduce forgetting under tight memory budgets without storing historical images.
-
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.
-
Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation
RAHA applies rank-aware hyperbolic alignment to vision-language dataset distillation by enforcing geodesic alignment in the shared low-rank range and regularizing the residual subspace for improved transfer.
-
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.