Diversity Without Labels: Task-Agnostic Coreset Selection Across Perception and Action
Read the original on arXiv Computer Vision →CoreDNA is an unsupervised, task‑agnostic coreset selection method that uses neuron activations from vision foundation models to build per‑image and per‑dataset distributions. By comparing each image’s distribution to the overall dataset distribution, it captures both low‑level visual structure and high‑level semantic information across layers, identifying high‑quality samples in the tails of the last layer’s activation statistics. The method achieves state‑of‑the‑art performance across image classification, semantic segmentation, depth estimation, and imitation learning for driving and mobile manipulation, demonstrating broad generalization without task‑specific tailoring.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.