Comparison of self-supervised in-domain and supervised out-domain transfer learning for bird species recognition

arXiv:2404.17252v1 Announce Type: new
Abstract: Transferring the weights of a pre-trained model to assist another task has become a crucial part of modern deep learning, particularly in data-scarce scenarios. Pre-training refers to the initial step of training models outside the current task of interest, typically on another dataset. It can be done via supervised models using human-annotated datasets or self-supervised models trained on unlabeled datasets. In both cases, many pre-trained models are available to fine-tune for the task of interest. …

abstract arxiv become bird comparison cs.cv cs.lg cs.sd current data deep learning domain modern part pre-trained model pre-training recognition species training training models transfer transfer learning type