相关论文: The Role of Pre-training Data in Transfer Learning

Popular zero-shot models suffer due to artifacts inherited from pretraining. One particularly detrimental issue, caused by unbalanced web-scale pretraining data, is mismatched label distribution. Existing approaches that seek to repair the…

Transfer-learning and meta-learning are two effective methods to apply knowledge learned from large data sources to new tasks. In few-class, few-shot target task settings (i.e. when there are only a few classes and training examples…

Most few-shot learning techniques are pre-trained on a large, labeled "base dataset". In problem domains where such large labeled datasets are not available for pre-training (e.g., X-ray, satellite images), one must resort to pre-training…

In this paper we present a technique to train neural network models on small amounts of data. Current methods for training neural networks on small amounts of rich data typically rely on strategies such as fine-tuning a pre-trained neural…

Domain adaptation of neural networks commonly relies on three training phases: pretraining, selected data training and then fine tuning. Data selection improves target domain generalization by training further on pretraining data identified…

Transfer learning is beneficial by allowing the expressive features of models pretrained on large-scale datasets to be finetuned for the target task of smaller, more domain-specific datasets. However, there is a concern that these…

Recent algorithms with state-of-the-art few-shot classification results start their procedure by computing data features output by a large pretrained model. In this paper we systematically investigate which models provide the best…

Transfer learning is a machine learning technique that uses previously acquired knowledge from a source domain to enhance learning in a target domain by reusing learned weights. This technique is ubiquitous because of its great advantages…

Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to…

Conventional wisdom suggests that pre-training Vision Transformers (ViT) improves downstream performance by learning useful representations. Is this actually true? We investigate this question and find that the features and representations…

Deep learning techniques have revolutionised medical imaging, improving diagnostic accuracy and enabling both more accurate and earlier disease detection. However, the relationship between pre-training strategies and downstream performance…

As the landscape of large language models expands, efficiently finetuning for specific tasks becomes increasingly crucial. At the same time, the landscape of parameter-efficient finetuning methods rapidly expands. Consequently,…

For most natural language processing tasks, the dominant practice is to finetune large pretrained transformer models (e.g., BERT) using smaller downstream datasets. Despite the success of this approach, it remains unclear to what extent…

In transfer learning, only the last part of the networks - the so-called head - is often fine-tuned. Representation similarity analysis shows that the most significant change still occurs in the head even if all weights are updatable.…

Deep neural networks produce state-of-the-art results when trained on a large number of labeled examples but tend to overfit when small amounts of labeled examples are used for training. Creating a large number of labeled examples requires…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

Most of the recent few-shot learning (FSL) algorithms are based on transfer learning, where a model is pre-trained using a large amount of source data, and the pre-trained model is fine-tuned using a small amount of target data. In transfer…

Supervised deep learning methods for performing audio source separation can be very effective in domains where there is a large amount of training data. While some music domains have enough data suitable for training a separation system,…

In medical image segmentation tasks, the scarcity of labeled training data poses a significant challenge when training deep neural networks. When using U-Net-style architectures, it is common practice to address this problem by pretraining…

Over the past decade, the field of machine learning has experienced remarkable advancements. While image recognition systems have achieved impressive levels of accuracy, they continue to rely on extensive training datasets. Additionally, a…