Deep neural networks are typically trained under a supervised learning framework where a model learns a single task using labeled data. Instead of relying solely on labeled data, practitioners can harness unlabeled or related data to improve model performance, which is often more accessible and ubiquitous. Self-supervised pre-training for transfer learning is becoming an increasingly popular technique to improve state-of-the-art results using unlabeled data. It involves first pre-training a model on a large amount of unlabeled data, then adapting the model to target tasks of interest. In this review, we survey self-supervised learning methods and their applications within the sequential transfer learning framework. We provide an overview of the taxonomy for self-supervised learning and transfer learning, and highlight some prominent methods for designing pre-training tasks across different domains. Finally, we discuss recent trends and suggest areas for future investigation.

When tasks change over time, meta-transfer learning seeks to improve the efficiency of learning a new task via both meta-learning and transfer-learning. While the standard attention has been effective in a variety of settings, we question its effectiveness in improving meta-transfer learning since the tasks being learned are dynamic and the amount of context can be substantially smaller. In this paper, using a recently proposed meta-transfer learning model, Sequential Neural Processes (SNP), we first empirically show that it suffers from a similar underfitting problem observed in the functions inferred by Neural Processes. However, we further demonstrate that unlike the meta-learning setting, the standard attention mechanisms are not effective in meta-transfer setting. To resolve, we propose a new attention mechanism, Recurrent Memory Reconstruction (RMR), and demonstrate that providing an imaginary context that is recurrently updated and reconstructed with interaction is crucial in achieving effective attention for meta-transfer learning. Furthermore, incorporating RMR into SNP, we propose Attentive Sequential Neural Processes-RMR (ASNP-RMR) and demonstrate in various tasks that ASNP-RMR significantly outperforms the baselines.

Machine learning algorithms typically require abundant data under a stationary environment. However, environments are nonstationary in many real-world applications. Critical issues lie in how to effectively adapt models under an ever-changing environment. We propose a method for transferring knowledge from a source domain to a target domain via $\ell_1$ regularization. We incorporate $\ell_1$ regularization of differences between source parameters and target parameters, in addition to an ordinary $\ell_1$ regularization. Hence, our method yields sparsity for both the estimates themselves and changes of the estimates. The proposed method has a tight estimation error bound under a stationary environment, and the estimate remains unchanged from the source estimate under small residuals. Moreover, the estimate is consistent with the underlying function, even when the source estimate is mistaken due to nonstationarity. Empirical results demonstrate that the proposed method effectively balances stability and plasticity.

Transfer learning can be said as a shortcut to solving complex machine learning problems. In simple words, this learning is used to enhance the learning of the model, shorten the time as well as make the learning process quick for the current task. This technique can be applied in computer vision when the model has to learn from images or videos and in NLP techniques. In this article, we list down the top 9 free resources in Transfer Learning one must-read. About: This tutorial is provided by the developers of TensorFlow, where you will learn how to classify images of cats and dogs by using transfer learning from a pre-trained network.

We propose a novel framework that unifies and extends existing methods of transfer learning (TL) for regression. To bridge a pretrained source model to the model on a target task, we introduce a density-ratio reweighting function, which is estimated through the Bayesian framework with a specific prior distribution. By changing two intrinsic hyperparameters and the choice of the density-ratio model, the proposed method can integrate three popular methods of TL: TL based on cross-domain similarity regularization, a probabilistic TL using the density-ratio estimation, and fine-tuning of pretrained neural networks. Moreover, the proposed method can benefit from its simple implementation without any additional cost; the model can be fully trained using off-the-shelf libraries for supervised learning in which the original output variable is simply transformed to a new output. We demonstrate its simplicity, generality, and applicability using various real data applications.

Transfer learning involves taking information and insight from one problem domain and applying it to a new problem domain. Although widely used in practice, theory for transfer learning remains less well-developed. To address this, we prove several novel results related to transfer learning, showing the need to carefully select which sets of information to transfer and the need for dependence between transferred information and target problems. Furthermore, we prove how the degree of probabilistic change in an algorithm using transfer learning places an upper bound on the amount of improvement possible. These results build on the algorithmic search framework for machine learning, allowing the results to apply to a wide range of learning problems using transfer.

Pretraining has become a standard technique in computer vision and natural language processing, which usually helps to improve performance substantially. Previously, the most dominant pretraining method is transfer learning (TL), which uses labeled data to learn a good representation network. Recently, a new pretraining approach -- self-supervised learning (SSL) -- has demonstrated promising results on a wide range of applications. SSL does not require annotated labels. It is purely conducted on input data by solving auxiliary tasks defined on the input data examples. The current reported results show that in certain applications, SSL outperforms TL and the other way around in other applications. There has not been a clear understanding on what properties of data and tasks render one approach outperforms the other. Without an informed guideline, ML researchers have to try both methods to find out which one is better empirically. It is usually time-consuming to do so. In this work, we aim to address this problem. We perform a comprehensive comparative study between SSL and TL regarding which one works better under different properties of data and tasks, including domain difference between source and target tasks, the amount of pretraining data, class imbalance in source data, and usage of target data for additional pretraining, etc. The insights distilled from our comparative studies can help ML researchers decide which method to use based on the properties of their applications.

Most approaches in few-shot learning rely on costly annotated data related to the goal task domain during (pre-)training. Recently, unsupervised meta-learning methods have exchanged the annotation requirement for a reduction in few-shot classification performance. Simultaneously, in settings with realistic domain shift, common transfer learning has been shown to outperform supervised meta-learning. Building on these insights and on advances in self-supervised learning, we propose a transfer learning approach which constructs a metric embedding that clusters unlabeled prototypical samples and their augmentations closely together. This pre-trained embedding is a starting point for few-shot classification by summarizing class clusters and fine-tuning. We demonstrate that our self-supervised prototypical transfer learning approach ProtoTransfer outperforms state-of-the-art unsupervised meta-learning methods on few-shot tasks from the mini-ImageNet dataset. In few-shot experiments with domain shift, our approach even has comparable performance to supervised methods, but requires orders of magnitude fewer labels.

The most advanced framework for dense pose estimation for chimpanzees. It will help primatologists and other scientists study how chimps across Africa behave in the wild and in captive settings. The framework leverages a large-scale data set of unlabeled videos in the wild, a pretrained dense pose estimator for humans, and dense self-training techniques. This is a joint project in collaboration with our partners the Max Planck Institute for Evolutionary Anthropology (MPI EVA) and the Pan African Programme: The Cultured Chimpanzee, and their network of collaborators. We show that we can train a model to detect and recognize chimpanzees by transferring knowledge from existing detection, segmentation, and human dense pose labeling models.

This paper considers the estimation and prediction of a high-dimensional linear regression in the setting of transfer learning, using samples from the target model as well as auxiliary samples from different but possibly related regression models. When the set of "informative" auxiliary samples is known, an estimator and a predictor are proposed and their optimality is established. The optimal rates of convergence for prediction and estimation are faster than the corresponding rates without using the auxiliary samples. This implies that knowledge from the informative auxiliary samples can be transferred to improve the learning performance of the target problem. In the case that the set of informative auxiliary samples is unknown, we propose a data-driven procedure for transfer learning, called Trans-Lasso, and reveal its robustness to non-informative auxiliary samples and its efficiency in knowledge transfer. The proposed procedures are demonstrated in numerical studies and are applied to a dataset concerning the associations among gene expressions. It is shown that Trans-Lasso leads to improved performance in gene expression prediction in a target tissue by incorporating the data from multiple different tissues as auxiliary samples.