Research

Large Pretraining Datasets Don't Guarantee Robustness after Fine-Tuning in Image Classification

Single source1 source7 Oct 2026

arXiv:2410.21582v4 Announce Type: replace-cross Abstract: Large-scale pretrained models are widely leveraged as foundations for learning new specialized tasks via fine-tuning, with the goal of maintaining the general performance of the model while allowing it

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2410.21582

← Back to all developments · Signals are a development reported by more than one source. See the methodology.