Related papers: Machine learning with limited data

Few-shot learning is devoted to training a model on few samples. Most of these approaches learn a model based on a pixel-level or global-level feature representation. However, using global features may lose local information, and using…

This manuscript presents a series of my selected contributions to the topic of label-efficient learning in computer vision and remote sensing. The central focus of this research is to develop and adapt methods that can learn effectively…

Recent progress in few-shot learning promotes a more realistic cross-domain setting, where the source and target datasets are from different domains. Due to the domain gap and disjoint label spaces between source and target datasets, their…

As unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. The question is how to effectively make use of such data. In this work, we revisit the self-training technique for…

Few-shot learning aims to train models that can be generalized to novel classes with only a few samples. Recently, a line of works are proposed to enhance few-shot learning with accessible semantic information from class names. However,…

Business analytics and machine learning have become essential success factors for various industries - with the downside of cost-intensive gathering and labeling of data. Few-shot learning addresses this challenge and reduces data gathering…

We propose regression networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each class. In high dimensional embedding…

Despite the advancement of supervised image recognition algorithms, their dependence on the availability of labeled data and the rapid expansion of image categories raise the significant challenge of zero-shot learning. Zero-shot learning…

Few-shot learning often involves metric learning-based classifiers, which predict the image label by comparing the distance between the extracted feature vector and class representations. However, applying global pooling in the backend of…

Weakly-supervised object detection attempts to limit the amount of supervision by dispensing the need for bounding boxes, but still assumes image-level labels on the entire training set. In this work, we study the problem of training an…

Few-shot classification tasks aim to classify images in query sets based on only a few labeled examples in support sets. Most studies usually assume that each image in a task has a single and unique class association. Under these…

Few-shot classification aims to recognize unseen classes with few labeled samples from each class. Many meta-learning models for few-shot classification elaborately design various task-shared inductive bias (meta-knowledge) to solve such…

This paper addresses unsupervised few-shot object recognition, where all training images are unlabeled, and test images are divided into queries and a few labeled support images per object class of interest. The training and test images do…

Few-shot and zero-shot text classification aim to recognize samples from novel classes with limited labeled samples or no labeled samples at all. While prevailing methods have shown promising performance via transferring knowledge from seen…

Device-free wireless indoor localization is an essential technology for the Internet of Things (IoT), and fingerprint-based methods are widely used. A common challenge to fingerprint-based methods is data collection and labeling. This paper…

Few-shot open-set recognition aims to classify both seen and novel images given only limited training data of seen classes. The challenge of this task is that the model is required not only to learn a discriminative classifier to classify…

The success of deep learning methods hinges on the availability of large training datasets annotated for the task of interest. In contrast to human intelligence, these methods lack versatility and struggle to learn and adapt quickly to new…

The challenge in few-shot learning is that available data is not enough to capture the underlying distribution. To mitigate this, two emerging directions are (a) using local image representations, essentially multiplying the amount of data…

Recent papers have suggested that transfer learning can outperform sophisticated meta-learning methods for few-shot image classification. We take this hypothesis to its logical conclusion, and suggest the use of an ensemble of high-quality,…

We propose a method that can perform one-class classification given only a small number of examples from the target class and none from the others. We formulate the learning of meaningful features for one-class classification as a…