Article

We use a frozen text encoder on image captions as a lightweight training-time auxiliary objective for image classifiers. The text components are drop.p.ed at inference, leaving a fast, unimodal vision model. Accuracy on ImageNet improves by up to +2.7 p.p. and downstream transfer by +1.0 p.p. on average, outperforming vision knowledge distillation at a fraction of the compute.

We introduce SubZeroCore, a novel, training-free coreset selection method that integrates submodular coverage and density into a single, unified objective.

We improve the training of vision transformers by segmenting and recombining objects and backgrounds from datasets. This makes the transformers more accurate, as well as more robust.

We speed up diffusion classifiers by utilizing a label hierarchy and pruning unrelated paths.

We improve dataset distillation by distilling only a representative coreset.