Related papers: Effective training of deep convolutional neural ne…
This paper considers the problem of inferring image labels from images when only a few annotated examples are available at training time. This setup is often referred to as low-shot learning, where a standard approach is to re-train the…
In this paper, we present a simple and efficient method for training deep neural networks in a semi-supervised setting where only a small portion of training data is labeled. We introduce self-ensembling, where we form a consensus…
Deep learning algorithms have demonstrated state-of-the-art performance in various tasks of image restoration. This was made possible through the ability of CNNs to learn from large exemplar sets. However, the latter becomes an issue for…
One recent research demonstrated successful application of the label alignment property for unsupervised domain adaptation in a linear regression settings. Instead of regularizing representation learning to be domain invariant, the research…
Active learning aims to develop label-efficient algorithms by querying the most informative samples to be labeled by an oracle. The design of efficient training methods that require fewer labels is an important research direction that…
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.…
In this paper, we study the problem of semi-supervised image recognition, which is to learn classifiers using both labeled and unlabeled images. We present Deep Co-Training, a deep learning based method inspired by the Co-Training…
Semi-supervised learning has the potential to improve the data-efficiency of training data-hungry deep neural networks, which is especially important for medical image analysis tasks where labeled data is scarce. In this work, we present a…
The availability of large labeled datasets has allowed Convolutional Network models to achieve impressive recognition results. However, in many settings manual annotation of the data is impractical; instead our data has noisy labels, i.e.…
Data-efficient image classification is a challenging task that aims to solve image classification using small training data. Neural network-based deep learning methods are effective for image classification, but they typically require…
We present a novel approach to leverage large unlabeled datasets by pre-training state-of-the-art deep neural networks on randomly-labeled datasets. Specifically, we train the neural networks to memorize arbitrary labels for all the samples…
The deep neural networks used in modern computer vision systems require enormous image datasets to train them. These carefully-curated datasets typically have a million or more images, across a thousand or more distinct categories. The…
With their combined spectral depth and geometric resolution, hyperspectral remote sensing images embed a wealth of complex, non-linear information that challenges traditional computer vision techniques. Yet, deep learning methods known for…
Image classification systems recently made a giant leap with the advancement of deep neural networks. However, these systems require an excessive amount of labeled data to be adequately trained. Gathering a correctly annotated dataset is…
In semantic segmentation, the creation of pixel-level labels for training data incurs significant costs. To address this problem, semi-supervised learning, which utilizes a small number of labeled images alongside unlabeled images to…
Multi-label image classification allows predicting a set of labels from a given image. Unlike multiclass classification, where only one label per image is assigned, such a setup is applicable for a broader range of applications. In this…
We present a technique to improve the transferability of deep representations learned on small labeled datasets by introducing self-supervised tasks as auxiliary loss functions. While recent approaches for self-supervised learning have…
In this paper, we study how the granularity of pretraining labels affects the generalization of deep neural networks in image classification tasks. We focus on the "fine-to-coarse" transfer learning setting, where the pretraining label…
In the field of medical imaging, the advent of deep learning, especially the application of convolutional neural networks (CNNs) has revolutionized the analysis and interpretation of medical images. Nevertheless, deep learning methods…
Transfer learning has emerged as a powerful methodology for adapting pre-trained deep neural networks on image recognition tasks to new domains. This process consists of taking a neural network pre-trained on a large feature-rich source…