Dataset Condensation with Distribution Matching

By Bo Zhao, Hakan Bilen. IEEE Workshop/Winter Conference on Applications of Computer Vision, 2021

485 citations recorded by the source corpus.

Computational cost of training state-of-the-art deep models in many learning problems is rapidly increasing due to more sophisticated models and larger datasets. A recent promising direction for reducing training cost is dataset condensation that aims to replace the original large training set with a significantly smaller learned synthetic set while preserving the original information. While training deep models on the small set of condensed images can be extremely fast, their synthesis remains computationally expensive due to the complex bi-level optimization and secondorder derivative computation. In this work, we propose a simple yet effective method that synthesizes condensed images by matching feature distributions of the synthetic and original training images in many sampled embedding spaces. Our method significantly reduces the synthesis cost while achieving comparable or better performance. Thanks to its efficiency, we apply our method to more realistic and larger datasets with sophisticated neural architectures and obtain a significant performance boost1. We also show promising practical benefits of our method in continual learning and neural architecture search.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c03f42a6686eb5fa8b62088c4c2b5545bc60ebdc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Dataset Distillation by Matching Training Trajectories (2022, methodology): “To generate the distilled images for our method, we employ the distillation process detailed in the previous section and Algorithm 1, using the same suite of differentiable aug-mentations as done in previous work [45, 46].”