activity
20232025
collaborators

5 papers

cs.CV2025

OD3: Optimization-free Dataset Distillation for Object Detection

Salwa K. Al Khatib, Ahmed ElHagry, Shitong Shao +1

Training large neural networks on large-scale datasets requires substantial computational resources, particularly for dense prediction tasks such as object detection. Although data…

cs.CV2024

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…

cs.CV2024

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…

cs.LG2024

Elucidating the Design Space of Dataset Condensation

Shitong Shao, Zikai Zhou, Huanran Chen +1

Dataset condensation, a concept within data-centric learning, efficiently transfers critical attributes from an original dataset to a synthetic version, maintaining both diversity…

cs.CV2023

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,…