相关论文: Few-Shot Text Ranking with Meta Adapted Synthetic …

Neural Networks trained with gradient descent are known to be susceptible to catastrophic forgetting caused by parameter shift during the training process. In the context of Neural Machine Translation (NMT) this results in poor performance…

The performance of machine learning algorithms is known to be negatively affected by possible mismatches between training (source) and test (target) data distributions. In fact, this problem emerges whenever an acoustic scene classification…

The great majority of languages in the world are considered under-resourced for the successful application of deep learning methods. In this work, we propose a meta-learning approach to document classification in limited-resource setting…

Domain adaptation (DA) aims at transferring knowledge from a labeled source domain to an unlabeled target domain. Though many DA theories and algorithms have been proposed, most of them are tailored into classification settings and may fail…

Adapting deep learning models to new domains often requires computationally intensive retraining and risks catastrophic forgetting. While fine-tuning enables domain-specific adaptation, it can reduce robustness to distribution shifts,…

Few-shot relation classification seeks to classify incoming query instances after meeting only few support instances. This ability is gained by training with large amount of in-domain annotated data. In this paper, we tackle an even harder…

For unsupervised domain adaptation (UDA), to alleviate the effect of domain shift, many approaches align the source and target domains in the feature space by adversarial learning or by explicitly aligning their statistics. However, the…

Few-shot slot tagging is an emerging research topic in the field of Natural Language Understanding (NLU). With sufficient annotated data from source domains, the key challenge is how to train and adapt the model to another target domain…

Practical sequence classification tasks in natural language processing often suffer from low training data availability for target classes. Recent works towards mitigating this problem have focused on transfer learning using embeddings…

The limited availability of ground truth relevance labels has been a major impediment to the application of supervised methods to ad-hoc retrieval. As a result, unsupervised scoring methods, such as BM25, remain strong competitors to deep…

Domain adaptation (DA) is the topical problem of adapting models from labelled source datasets so that they perform well on target datasets where only unlabelled or partially labelled data is available. Many methods have been proposed to…

Annotation-efficient segmentation of the numerous mitochondria instances from various electron microscopy (EM) images is highly valuable for biological and neuroscience research. Although unsupervised domain adaptation (UDA) methods can…

End-to-end learning methods have achieved impressive results in many areas of computer vision. At the same time, these methods still suffer from a degradation in performance when testing on new datasets that stem from a different…

Recent advances in deep learning, in particular enabled by hardware advances and big data, have provided impressive results across a wide range of computational problems such as computer vision, natural language, or reinforcement learning.…

Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which…

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…

Meta-learning has become a practical approach towards few-shot image classification, where "a strategy to learn a classifier" is meta-learned on labeled base classes and can be applied to tasks with novel classes. We remove the requirement…

Most research on domain adaptation has focused on the purely unsupervised setting, where no labeled examples in the target domain are available. However, in many real-world scenarios, a small amount of labeled target data is available and…

Few-shot visual recognition refers to recognize novel visual concepts from a few labeled instances. Many few-shot visual recognition methods adopt the metric-based meta-learning paradigm by comparing the query representation with class…

Few-shot Learning aims to learn classifiers for new classes with only a few training examples per class. Existing meta-learning or metric-learning based few-shot learning approaches are limited in handling diverse domains with various…