相关论文: Few-shot Transfer Learning for Knowledge Base Ques…

The limits of applicability of vision-and-language models are defined by the coverage of their training data. Tasks like vision question answering (VQA) often require commonsense and factual information beyond what can be learned from…

Through a simple multiple choice language prompt a VQA model can operate as a zero-shot image classifier, producing a classification label. Compared to typical image encoders, VQA models offer an advantage: VQA-produced image embeddings can…

Knowledge base question answering (KBQA) is a challenging task that aims to retrieve correct answers from large-scale knowledge bases. Existing attempts primarily focus on entity representation and final answer reasoning, which results in…

Few-shot Continual Relation Extraction is a crucial challenge for enabling AI systems to identify and adapt to evolving relationships in dynamic real-world domains. Traditional memory-based approaches often overfit to limited samples,…

Recent advances in deep learning have greatly propelled the research on semantic parsing. Improvement has since been made in many downstream tasks, including natural language interface to web APIs, text-to-SQL generation, among others.…

Few-shot adaptation is a challenging problem in the context of simulation-to-real transfer in robotics, requiring safe and informative data collection. In physical systems, additional challenge may be posed by domain noise, which is present…

Training a neural network model that can quickly adapt to a new task is highly desirable yet challenging for few-shot learning problems. Recent few-shot learning methods mostly concentrate on developing various meta-learning strategies from…

Relation detection is a core component for Knowledge Base Question Answering (KBQA). In this paper, we propose a KB relation detection model via multi-view matching which utilizes more useful information extracted from question and KB. The…

Knowledge base question answering (KBQA) aims to answer user questions in natural language using rich human knowledge stored in large KBs. As current KBQA methods struggle with unseen knowledge base elements at test time,we introduce…

Few-shot learning (FSL) techniques seek to learn the underlying patterns in data using fewer samples, analogous to how humans learn from limited experience. In this limited-data scenario, the challenges associated with deep neural networks,…

Few-Shot Class-Incremental Learning presents an extension of the Class Incremental Learning problem where a model is faced with the problem of data scarcity while addressing the catastrophic forgetting problem. This problem remains an open…

Recent studies on Knowledge Base Question Answering (KBQA) have shown great progress on this task via better question understanding. Previous works for encoding questions mainly focus on the word sequences, but seldom consider the…

We study the problem of visual question answering (VQA) in images by exploiting supervised domain adaptation, where there is a large amount of labeled data in the source domain but only limited labeled data in the target domain with the…

Existing studies on question answering on knowledge bases (KBQA) mainly operate with the standard i.i.d assumption, i.e., training distribution over questions is the same as the test distribution. However, i.i.d may be neither reasonably…

We propose a Paired Few-shot GAN (PFS-GAN) model for learning generators with sufficient source data and a few target data. While generative model learning typically needs large-scale training data, our PFS-GAN not only uses the concept of…

Few-shot learning has drawn researchers' attention to overcome the problem of data scarcity. Recently, large pre-trained language models have shown great performance in few-shot learning for various downstream tasks, such as question…

Few-shot classification consists of a training phase where a model is learned on a relatively large dataset and an adaptation phase where the learned model is adapted to previously-unseen tasks with limited labeled samples. In this paper,…

Few-shot learning aims to generalize to novel classes with only a few samples with class labels. Research in few-shot learning has borrowed techniques from transfer learning, metric learning, meta-learning, and Bayesian methods. These…

We study the ability of foundation models to learn representations for classification that are transferable to new, unseen classes. Recent results in the literature show that representations learned by a single classifier over many classes…

Deep networks are prone to performance degradation when there is a domain shift between the source (training) data and target (test) data. Recent test-time adaptation methods update batch normalization layers of pre-trained source models…