Related papers: Auto-Transfer: Learning to Route Transferrable Rep…
The ability to automatically learn task specific feature representations has led to a huge success of deep learning methods. When large training data is scarce, such as in medical imaging problems, transfer learning has been very effective.…
The field of image classification has shown an outstanding success thanks to the development of deep learning techniques. Despite the great performance obtained, most of the work has focused on natural images ignoring other domains like…
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…
Deep transfer learning (DTL) has formed a long-term quest toward enabling deep neural networks (DNNs) to reuse historical experiences as efficiently as humans. This ability is named knowledge transferability. A commonly used paradigm for…
Reinforcement learning (RL) can automate a wide variety of robotic skills, but learning each new skill requires considerable real-world data collection and manual representation engineering to design policy classes or features. Using deep…
Transfer learning, which is to improve the learning performance in the target domain by leveraging useful knowledge from the source domain, often requires that those two domains are very close, which limits its application scope. Recently,…
Deep learning models exhibit limited generalizability across different domains. Specifically, transferring knowledge from available entangled domain features(source/target domain) and categorical features to new unseen categorical features…
In computer vision, one is often confronted with problems of domain shifts, which occur when one applies a classifier trained on a source dataset to target data sharing similar characteristics (e.g. same classes), but also different latent…
Deep neural networks (DNNs) are highly susceptible to adversarial examples--subtle perturbations applied to inputs that are often imperceptible to humans yet lead to incorrect model predictions. In black-box scenarios, however, existing…
Feature-based transfer is one of the most effective methodologies for transfer learning. Existing studies usually assume that the learned new feature representation is \emph{domain-invariant}, and thus train a transfer model $\mathcal{M}$…
Statistical analysis of network data has attracted considerable attention in recent years, due to the rapid advancement of well-trained network models and the accessibility of large public network datasets. In this article, we propose a…
Despite the remarkable success of Deep RL in learning control policies from raw pixels, the resulting models do not generalize. We demonstrate that a trained agent fails completely when facing small visual changes, and that…
The computer vision community is witnessing an unprecedented rate of new tasks being proposed and addressed, thanks to the deep convolutional networks' capability to find complex mappings from X to Y. The advent of each task often…
Transfer learning can boost the performance on the targettask by leveraging the knowledge of the source domain. Recent worksin neural architecture search (NAS), especially one-shot NAS, can aidtransfer learning by establishing sufficient…
The goal of transfer learning is to improve the performance of target learning task by leveraging information (or transferring knowledge) from other related tasks. In this paper, we examine the problem of transfer distance metric learning…
With the emergence of large-scale pre-trained neural networks, methods to adapt such "foundation" models to data-limited downstream tasks have become a necessity. Fine-tuning, preference optimization, and transfer learning have all been…
Graphs provide a powerful means for representing complex interactions between entities. Recently, deep learning approaches are emerging for representing and modeling graph-structured data, although the conventional deep learning methods…
In this paper, we consider the problem of learning a linear regression model on a data domain of interest (target) given few samples. To aid learning, we are provided with a set of pre-trained regression models that are trained on…
There are numerous advantages of deep neural network surrogate modeling for response time-history prediction. However, due to the high cost of refined numerical simulations and actual experiments, the lack of data has become an unavoidable…
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…