Related papers: Few-shot learning with attention-based sequence-to…

In intent detection tasks, leveraging meaningful semantic information from intent labels can be particularly beneficial for few-shot scenarios. However, existing few-shot intent detection methods either ignore the intent labels, (e.g.…

Although deep learning approaches have stood out in recent years due to their state-of-the-art results, they continue to suffer from catastrophic forgetting, a dramatic decrease in overall performance when training with new classes added…

Few-shot learning aims to train models that can recognize novel classes given just a handful of labeled examples, known as the support set. While the field has seen notable advances in recent years, they have often focused on multi-class…

Few-shot crosslingual transfer has been shown to outperform its zero-shot counterpart with pretrained encoders like multilingual BERT. Despite its growing popularity, little to no attention has been paid to standardizing and analyzing the…

We introduce a method called the Expansion mechanism that processes the input unconstrained by the number of elements in the sequence. By doing so, the model can learn more effectively compared to traditional attention-based approaches. To…

Few-shot learning (FSL) aims to learn models that generalize to novel classes with limited training samples. Recent works advance FSL towards a scenario where unlabeled examples are also available and propose semi-supervised FSL methods.…

We study the application of large language models to zero-shot and few-shot classification of tabular data. We prompt the large language model with a serialization of the tabular data to a natural-language string, together with a short…

Audio-visual speech recognition (AVSR) system is thought to be one of the most promising solutions for robust speech recognition, especially in noisy environment. In this paper, we propose a novel multimodal attention based method for…

Detecting rare objects from a few examples is an emerging problem. Prior works show meta-learning is a promising approach. But, fine-tuning techniques have drawn scant attention. We find that fine-tuning only the last layer of existing…

The recent advances in deep learning are mostly driven by availability of large amount of training data. However, availability of such data is not always possible for specific tasks such as speaker recognition where collection of large…

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,…

Human educators possess an intrinsic ability to anticipate and seek educational explanations from students, which drives them to pose thought-provoking questions when students cannot articulate these explanations independently. We aim to…

Few-shot object detection, the problem of modelling novel object detection categories with few training instances, is an emerging topic in the area of few-shot learning and object detection. Contemporary techniques can be divided into two…

Convolutional neural networks (CNNs) are one of the driving forces for the advancement of computer vision. Despite their promising performances on many tasks, CNNs still face major obstacles on the road to achieving ideal machine…

Transferring knowledge from one domain to another is of practical importance for many tasks in natural language processing, especially when the amount of available data in the target domain is limited. In this work, we propose a novel…

Recent research showed promising results on combining pretrained language models (LMs) with canonical utterance for few-shot semantic parsing. The canonical utterance is often lengthy and complex due to the compositional structure of formal…

Recently, the end-to-end training approach for neural beamformer-supported multi-channel ASR has shown its effectiveness in multi-channel speech recognition. However, the integration of multiple modules makes it more difficult to perform…

The success of deep learning models is heavily tied to the use of massive amount of labeled data and excessively long training time. With the emergence of intelligent edge applications that use these models, the critical challenge is to…

Current large open vision models could be useful for one and few-shot object recognition. Nevertheless, gradient-based re-training solutions are costly. On the other hand, open-vocabulary object detection models bring closer visual and…

Currently available benchmarks for few-shot learning (machine learning with few training examples) are limited in the domains they cover, primarily focusing on image classification. This work aims to alleviate this reliance on image-based…