Related papers: Adversarially-Trained Deep Nets Transfer Better: I…
Though deep neural networks perform challenging tasks excellently, they are susceptible to adversarial examples, which mislead classifiers by applying human-imperceptible perturbations on clean inputs. Under the query-free black-box…
Deep reinforcement learning agents have recently been successful across a variety of discrete and continuous control tasks; however, they can be slow to train and require a large number of interactions with the environment to learn a…
Knowledge transfer impacts the performance of deep learning -- the state of the art for image classification tasks, including automated melanoma screening. Deep learning's greed for large amounts of training data poses a challenge for…
A commonly accepted hypothesis is that models with higher accuracy on Imagenet perform better on other downstream tasks, leading to much research dedicated to optimizing Imagenet accuracy. Recently this hypothesis has been challenged by…
One desired capability for machines is the ability to transfer their knowledge of one domain to another where data is (usually) scarce. Despite ample adaptation of transfer learning in various deep learning applications, we yet do not…
In recent years, representation learning approaches have disrupted many multimedia computing tasks. Among those approaches, deep convolutional neural networks (CNNs) have notably reached human level expertise on some constrained image…
Contrastive learning has shown to learn better quality representations than models trained using cross-entropy loss. They also transfer better to downstream datasets from different domains. However, little work has been done to explore the…
As the application of deep learning has expanded to real-world problems with insufficient volume of training data, transfer learning recently has gained much attention as means of improving the performance in such small-data regime.…
Domain adaptation is widely used in learning problems lacking labels. Recent studies show that deep adversarial domain adaptation models can make markable improvements in performance, which include symmetric and asymmetric architectures.…
We attempt to interpret how adversarially trained convolutional neural networks (AT-CNNs) recognize objects. We design systematic approaches to interpret AT-CNNs in both qualitative and quantitative ways and compare them with normally…
Generative adversarial networks (GANs) have remarkably advanced in diverse domains, especially image generation and editing. However, the misuse of GANs for generating deceptive images, such as face replacement, raises significant security…
Machine learning is used for inference and decision making in wearable sensor systems. However, recent studies have found that machine learning algorithms are easily fooled by the addition of adversarial perturbations to their inputs. What…
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…
This work studies training generative adversarial networks under the federated learning setting. Generative adversarial networks (GANs) have achieved advancement in various real-world applications, such as image editing, style transfer,…
Convolutional neural networks require numerous data for training. Considering the difficulties in data collection and labeling in some specific tasks, existing approaches generally use models pre-trained on a large source domain (e.g.…
Transfer of pre-trained representations can improve sample efficiency and reduce computational requirements for new tasks. However, representations used for transfer are usually generic, and are not tailored to a particular distribution of…
The recent success of deep neural networks relies on massive amounts of labeled data. For a target task where labeled data is unavailable, domain adaptation can transfer a learner from a different source domain. In this paper, we propose a…
The transferability of adversarial examples allows for the attack on unknown deep neural networks (DNNs), posing a serious threat to many applications and attracting great attention. In this paper, we improve the transferability of…
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…
Deep learning has raised hopes and expectations as a general solution for many applications; indeed it has proven effective, but it also showed a strong dependence on large quantities of data. Luckily, it has been shown that, even when data…