Related papers: Inferring Latent Class Statistics from Text for Ro…

The CLIP (Contrastive Language-Image Pre-training) model and its variants are becoming the de facto backbone in many applications. However, training a CLIP model from hundreds of millions of image-text pairs can be prohibitively expensive.…

Intent Detection is one of the core tasks of dialog systems. Few-shot Intent Detection is challenging due to limited number of annotated utterances for novel classes. Generalized Few-shot intent detection is more realistic but challenging…

There has been a significant progress in text conditional image generation models. Recent advancements in this field depend not only on improvements in model structures, but also vast quantities of text-image paired datasets. However,…

This paper studies few-shot segmentation, which is a task of predicting foreground mask of unseen classes by a few of annotations only, aided by a set of rich annotations already existed. The existing methods mainly focus the task on…

The human visual system has the remarkably ability to be able to effortlessly learn novel concepts from only a few examples. Mimicking the same behavior on machine learning vision systems is an interesting and very challenging research…

We study few-shot learning in natural language domains. Compared to many existing works that apply either metric-based or optimization-based meta-learning to image domain with low inter-task variance, we consider a more realistic setting,…

Low-shot image classification is a fundamental task in computer vision, and the emergence of large-scale vision-language models such as CLIP has greatly advanced the forefront of research in this field. However, most existing CLIP-based…

This paper proposes Dynamic Memory Induction Networks (DMIN) for few-shot text classification. The model utilizes dynamic routing to provide more flexibility to memory-based few-shot learning in order to better adapt the support sets, which…

Recently, vision model pre-training has evolved from relying on manually annotated datasets to leveraging large-scale, web-crawled image-text data. Despite these advances, there is no pre-training method that effectively exploits the…

Most of the literature around text classification treats it as a supervised learning problem: given a corpus of labeled documents, train a classifier such that it can accurately predict the classes of unseen documents. In industry, however,…

Learning from one or few visual examples is one of the key capabilities of humans since early infancy, but is still a significant challenge for modern AI systems. While considerable progress has been achieved in few-shot learning from a few…

People typically learn through exposure to visual concepts associated with linguistic descriptions. For instance, teaching visual object categories to children is often accompanied by descriptions in text or speech. In a machine learning…

Few-shot learning has been extensively explored to address problems where the amount of labeled samples is very limited for some classes. In the semi-supervised few-shot learning setting, substantial quantities of unlabeled samples are…

Text classification is usually studied by labeling natural language texts with relevant categories from a predefined set. In the real world, new classes might keep challenging the existing system with limited labeled data. The system should…

Multi-modal learning has become increasingly popular due to its ability to leverage information from different data sources (e.g., text and images) to improve the model performance. Recently, CLIP has emerged as an effective approach that…

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…

Humans possess remarkable ability to accurately classify new, unseen images after being exposed to only a few examples. Such ability stems from their capacity to identify common features shared between new and previously seen images while…

Detecting social bias in text is challenging due to nuance, subjectivity, and difficulty in obtaining good quality labeled datasets at scale, especially given the evolving nature of social biases and society. To address these challenges, we…

Integrating image and text data through multi-modal learning has emerged as a new approach in medical imaging research, following its successful deployment in computer vision. While considerable efforts have been dedicated to establishing…

To advance argumentative stance prediction as a multimodal problem, the First Shared Task in Multimodal Argument Mining hosted stance prediction in crucial social topics of gun control and abortion. Our exploratory study attempts to…