7 citations · 13 across the 6 of their papers we have counts for
6 papers · 1 filter
TRIM: Scalable 3D Gaussian Diffusion Inference with Temporal and Spatial Trimming
Zeyuan Yin, Xiaoming Liu
Recent advances in 3D Gaussian diffusion models suffer from time-intensive denoising and post-denoising processing due to the massive number of Gaussian primitives, resulting in sl…
DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation
Zhiqiang Shen, Ammar Sherif, Zeyuan Yin +1
Recent advances in dataset distillation have led to solutions in two main directions. The conventional batch-to-batch matching mechanism is ideal for small-scale datasets and inclu…
Self-supervised Dataset Distillation: A Good Compression Is All You Need
Muxin Zhou, Zeyuan Yin, Shitong Shao +1
Dataset distillation aims to compress information from a large-scale original dataset to a new compact dataset while striving to preserve the utmost degree of the original data inf…
Dataset Distillation via Curriculum Data Synthesis in Large Data Era
Zeyuan Yin, Zhiqiang Shen
Dataset distillation or condensation aims to generate a smaller but representative subset from a large dataset, which allows a model to be trained more efficiently, meanwhile evalu…
Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching
Shitong Shao, Zeyuan Yin, Muxin Zhou +2
The lightweight "local-match-global" matching introduced by SRe2L successfully creates a distilled dataset with comprehensive information on the full 224x224 ImageNet-1k. However,…
Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective
Zeyuan Yin, Eric Xing, Zhiqiang Shen
We present a new dataset condensation framework termed Squeeze, Recover and Relabel (SReL) that decouples the bilevel optimization of model and synthetic data during training,…