Learn More
We evaluate whether features extracted from the activation of a deep convolutional network trained in a fully supervised fashion on a large, fixed set of object recognition tasks can be re-purposed to novel generic tasks. Our generic tasks may differ significantly from the originally trained tasks and there may be insufficient labeled or unlabeled data to(More)
Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias on a standard benchmark. Fine-tuning deep models in a new domain can require a significant amount of data, which for many applications is simply not available. We propose a new CNN architecture which introduces an(More)
Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias. Fine-tuning deep models in a new domain can require a significant amount of labeled data, which for many applications is simply not available. We propose a new CNN architecture to exploit unlabeled and sparsely labeled(More)
A major challenge in scaling object detection is the difficulty of obtaining labeled images for large numbers of categories. Recently, deep convolutional neural networks (CNN) have emerged as clear winners on object classification benchmarks , in part due to training with 1.2M+ labeled classification images. Unfortunately , only a small fraction of those(More)
Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains. They also can improve recognition despite the presence of domain shift or dataset bias: several adversarial approaches to unsupervised domain adaptation have recently been introduced, which reduce the difference(More)
Dataset bias remains a significant barrier towards solving real world computer vision tasks. Though deep convolutional networks have proven to be a competitive approach for image classification, a question remains: have these models have solved the dataset bias problem? In general, training or fine-tuning a state-of-the-art deep model on a new domain(More)
We address the problem of adapting robotic perception from simulated to real-world environments. For many robotic control tasks, real training imagery is expensive to obtain, but a large amount of synthetic data is easy to generate through simulation. We propose a method that adapts representations using a small number of paired synthetic and real views of(More)
We propose a system for user-aided visual localization of desert imagery without the use of any metadata such as GPS readings, camera focal length, or field-of-view. The system makes use only of publicly available digital elevation models (DEMs) to rapidly and accurately locate photographs in non-urban environments such as deserts. Our system generates(More)
Real-world robotics problems often occur in domains that differ significantly from the robot’s prior training environment. For many robotic control tasks, real world experience is expensive to obtain, but data is easy to collect in either an instrumented environment or in simulation. We propose a novel domain adaptation approach for robot perception that(More)
Wilson disease (WD) is a monogenic autosomal-recessive disorder of copper accumulation that leads to liver failure and/or neurological deficits. WD is caused by mutations in ATP7B, a transporter that loads Cu(I) onto newly synthesized cupro-enzymes in the trans-Golgi network (TGN) and exports excess copper out of cells by trafficking from the TGN to the(More)