ActiveDC: Distribution Calibration for Active Finetuning

arXiv:2311.07634v3 Announce Type: replace
Abstract: The pretraining-finetuning paradigm has gained popularity in various computer vision tasks. In this paradigm, the emergence of active finetuning arises due to the abundance of large-scale data and costly annotation requirements. Active finetuning involves selecting a subset of data from an unlabeled pool for annotation, facilitating subsequent finetuning. However, the use of a limited number of training samples can lead to a biased distribution, potentially resulting in model overfitting. In this paper, we propose a …

abstract annotation arxiv computer computer vision cs.cv data distribution emergence finetuning paradigm pool pretraining requirements scale tasks type vision