Related papers: Anti-Transfer Learning for Task Invariance in Conv…
Continual learning of a stream of tasks is an active area in deep neural networks. The main challenge investigated has been the phenomenon of catastrophic forgetting or interference of newly acquired knowledge with knowledge from previous…
Attention plays a critical role in human visual experience. Furthermore, it has recently been demonstrated that attention can also play an important role in the context of applying artificial neural networks to a variety of tasks from…
The goal of semantic parsing is to map natural language to a machine interpretable meaning representation language (MRL). One of the constraints that limits full exploration of deep learning technologies for semantic parsing is the lack of…
Humans are incredibly good at transferring knowledge from one domain to another, enabling rapid learning of new tasks. Likewise, transfer learning has enabled enormous success in many computer vision problems using pretraining. However, the…
Transfer learning with models pretrained on ImageNet has become a standard practice in computer vision. Transfer learning refers to fine-tuning pretrained weights of a neural network on a downstream task, typically unrelated to ImageNet.…
In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch. When using fine-tuning, the underlying assumption is that the pre-trained model extracts generic features, which…
We propose a transfer learning method that utilizes data representations in a semiparametric regression model. Our aim is to perform statistical inference on the parameter of primary interest in the target model while accounting for…
Contrastive self-supervised learning methods famously produce high quality transferable representations by learning invariances to different data augmentations. Invariances established during pre-training can be interpreted as strong…
End-to-end neural TTS has shown improved performance in speech style transfer. However, the improvement is still limited by the available training data in both target styles and speakers. Additionally, degenerated performance is observed…
As the application space of language models continues to evolve, a natural question to ask is how we can quickly adapt models to new tasks. We approach this classic question from a continual learning perspective, in which we aim to continue…
Transfer learning is widely used for training machine learning models. Here, we study the role of transfer learning for training fully convolutional networks (FCNs) for medical image segmentation. Our experiments show that although transfer…
Transfer learning from high-resource languages is known to be an efficient way to improve end-to-end automatic speech recognition (ASR) for low-resource languages. Pre-trained or jointly trained encoder-decoder models, however, do not share…
Transfer learning aims to solve the data sparsity for a target domain by applying information of the source domain. Given a sequence (e.g. a natural language sentence), the transfer learning, usually enabled by recurrent neural network…
Transfer learning is a machine learning paradigm where knowledge from one problem is utilized to solve a new but related problem. While conceivable that knowledge from one task could be useful for solving a related task, if not executed…
This paper explores a new research problem of unsupervised transfer learning across multiple spatiotemporal prediction tasks. Unlike most existing transfer learning methods that focus on fixing the discrepancy between supervised tasks, we…
Transfer learning for deep neural networks is the process of first training a base network on a source dataset, and then transferring the learned features (the network's weights) to a second network to be trained on a target dataset. This…
This paper presents a transfer learning method in speech emotion recognition based on a Time-Delay Neural Network (TDNN) architecture. A major challenge in the current speech-based emotion detection research is data scarcity. The proposed…
Training deep neural networks for automatic speech recognition (ASR) requires large amounts of transcribed speech. This becomes a bottleneck for training robust models for accented speech which typically contains high variability in…
The availability of abundant labeled data in recent years led the researchers to introduce a methodology called transfer learning, which utilizes existing data in situations where there are difficulties in collecting new annotated data.…
Transfer learning has become a central paradigm in modern machine learning, yet it suffers from the long-standing problem of negative transfer, where leveraging source representations can harm rather than help performance on the target…