Dataset distillation (DD) aims to retain the training utility of a large dataset in a much smaller set of examples. For skeleton-based action recognition, this requires capturing discriminative motion variation without disrupting the geometry and temporal continuity of articulated bodies. Directly optimizing joint coor...
Yi Wei, Ya-Wen Zou, Wen-Qi Cai et al.· 0 citations
Dataset distillation (DD) condenses a large original dataset into a small distilled dataset with high training utility. Decoupled statistical matching methods substantially reduce distillation time and memory overhead while achieving strong performance. However, they typically supervise all distilled samples using runn...
Hong-Xu Ma, Guang Li, Shi-Jie Wang et al.· 0 citations
A classifier-derived guidance framework for diffusion-based medical dataset distillation is proposed that uses predictions from a pretrained noise-conditioned classifier to guide diffusion sampling through three objectives and characterize the configuration-dependent utility of classifier-derived guidance for compact s...
Shuai-Ling Du, Guang Li, Ren Togo et al.· Bioengineering· 0 citations
This work asks whether the union of separately distilled sets reproduces training on the union of the real data composability and shows that it can fail even when every source is distilled exactly and the total budget admits an exact joint distillate.
Guang Li, Takahiro Ogawa, M. Haseyama· 0 citations
DeCO uses attention rollout from a pretrained TransFG teacher to identify informative patches, applies spatial diversification to reduce redundant coverage, and organizes the resulting regions into class-wise evidence banks and consistently outperforms representative coreset and dataset-distillation baselines under dif...
Chuixuan Fan, Guang Li, Shi-Jie Wang et al.· 0 citations
This work proposes a saliency-driven distillation framework that constructs class-discriminative latent prototypes to enhance representativeness and generalization and demonstrates consistent performance improvements over strong baselines.
Yawen Zou, Wenqi Cai, Guang Li et al.· arXiv.org· 0 citations
Self-supervised representation-guided generative dataset distillation (SRG) is proposed, a framework that translates the SSL geometry into diffusion guidance and consistently outperforms the evaluated generative baselines across multiple datasets and IPC settings.
Mingzhuo Li, Guang Li, Linfeng Ye et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
