Efficient Transferability Assessment for Selection of Pre-trained Detectors

arXiv:2403.09432v1 Announce Type: new
Abstract: Large-scale pre-training followed by downstream fine-tuning is an effective solution for transferring deep-learning-based models. Since finetuning all possible pre-trained models is computational costly, we aim to predict the transferability performance of these pre-trained models in a computational efficient manner. Different from previous work that seek out suitable models for downstream classification and segmentation tasks, this paper studies the efficient transferability assessment of pre-trained object detectors. To this end, we build up a detector transferability benchmark …

abstract aim arxiv assessment computational cs.cv fine-tuning finetuning performance pre-trained models pre-training scale solution training type work