3 papers
cs.CV2025
Dataset Distillation for Pre-Trained Self-Supervised Vision Models
George Cazenavette, Antonio Torralba, Vincent Sitzmann
The task of dataset distillation aims to find a small set of synthetic images such that training a model on them reproduces the performance of the same model trained on a much larg…
cs.CV2025
DD-Ranking: Rethinking the Evaluation of Dataset Distillation
Zekai Li, Xinhao Zhong, Samir Khaki +49
In recent years, dataset distillation has provided a reliable solution for data compression, where models trained on the resulting smaller synthetic datasets achieve performance co…
cs.CV2025
Rethinking the Role of Spatial Mixing
George Cazenavette, Joel Julin, Simon Lucey
Until quite recently, the backbone of nearly every state-of-the-art computer vision model has been the 2D convolution. At its core, a 2D convolution simultaneously mixes informatio…