Related papers: Transfer Value Iteration Networks
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…
It has been demonstrated that deep neural networks outperform traditional machine learning. However, deep networks lack generalisability, that is, they will not perform as good as in a new (testing) set drawn from a different distribution…
As post-training processes utilize increasingly large datasets and base models continue to grow in size, the computational demands and implementation challenges of existing algorithms are escalating significantly. In this paper, we propose…
We propose a framework that learns a representation transferable across different domains and tasks in a label efficient manner. Our approach battles domain shift with a domain adversarial loss, and generalizes the embedding to novel task…
Learning to transfer visual attributes requires supervision dataset. Corresponding images with varying attribute values with the same identity are required for learning the transfer function. This largely limits their applications, because…
Transfer learning is a popular method for tuning pretrained (upstream) models for different downstream tasks using limited data and computational resources. We study how an adversary with control over an upstream model used in transfer…
Unsupervised domain translation has recently achieved impressive performance with Generative Adversarial Network (GAN) and sufficient (unpaired) training data. However, existing domain translation frameworks form in a disposable way where…
The existing internet-scale image and video datasets cover a wide range of everyday objects and tasks, bringing the potential of learning policies that generalize in diverse scenarios. Prior works have explored visual pre-training with…
Transfer learning aims to faciliate learning tasks in a label-scarce target domain by leveraging knowledge from a related source domain with plenty of labeled data. Often times we may have multiple domains with little or no labeled data as…
Graph neural networks (GNNs) build on the success of deep learning models by extending them for use in graph spaces. Transfer learning has proven extremely successful for traditional deep learning problems: resulting in faster training and…
In human learning, it is common to use multiple sources of information jointly. However, most existing feature learning approaches learn from only a single task. In this paper, we propose a novel multi-task deep network to learn…
In this paper, we study the problem of transfer learning with the attribute data. In the transfer learning problem, we want to leverage the data of the auxiliary and the target domains to build an effective model for the classification…
We train embodied neural networks to plan and navigate unseen complex 3D environments, emphasising real-world deployment. Rather than requiring prior knowledge of the agent or environment, the planner learns to model the state transitions…
Large-scale labeled training datasets have enabled deep neural networks to excel on a wide range of benchmark vision tasks. However, in many applications it is prohibitively expensive or time-consuming to obtain large quantities of labeled…
Transfer Learning is concerned with the application of knowledge gained from solving a problem to a different but related problem domain. In this paper, we propose a method and efficient algorithm for ranking and selecting representations…
Physics-informed neural network (PINN) is a data-driven solver for partial and ordinary differential equations(ODEs/PDEs). It provides a unified framework to address both forward and inverse problems. However, the complexity of the…
Common domain shift problem formulations consider the integration of multiple source domains, or the target domain during training. Regarding the generalization of machine learning models between different car interiors, we formulate the…
Classical Domain Adaptation methods acquire transferability by regularizing the overall distributional discrepancies between features in the source domain (labeled) and features in the target domain (unlabeled). They often do not…
Transfer in reinforcement learning refers to the notion that generalization should occur not only within a task but also across tasks. We propose a transfer framework for the scenario where the reward function changes between tasks but the…
In this paper, we analyze the effectiveness of transfer learning on classifying electronic components. Transfer learning reuses pre-trained models to save time and resources in building a robust classifier rather than learning from scratch.…