Related papers: Zero-Shot Text Classification via Self-Supervised …

With the advances of deep learning techniques, text generation is attracting increasing interest in the artificial intelligence (AI) community, because of its wide applications and because it is an essential component of AI. Traditional…

This work presents a tuning-free semantic segmentation framework based on classifying SAM masks by CLIP, which is universally applicable to various types of supervision. Initially, we utilize CLIP's zero-shot classification ability to…

Treating texts as images, combining prompts with textual labels for prompt tuning, and leveraging the alignment properties of CLIP have been successfully applied in zero-shot multi-label image recognition. Nonetheless, relying solely on…

The success of deep learning in computer vision is rooted in the ability of deep networks to scale up model complexity as demanded by challenging visual tasks. As complexity is increased, so is the need for large amounts of labeled data to…

Self-supervised models trained with a contrastive loss such as CLIP have shown to be very powerful in zero-shot classification settings. However, to be used as a zero-shot classifier these models require the user to provide new captions…

Recent approaches have shown that training deep neural networks directly on large-scale image-text pair collections enables zero-shot transfer on various recognition tasks. One central issue is how this can be generalized to object…

With increasing scale, large language models demonstrate both quantitative improvement and new qualitative capabilities, especially as zero-shot learners, like GPT-3. However, these results rely heavily on delicate prompt design and large…

Few-shot Learning aims to learn and distinguish new categories with a very limited number of available images, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional…

Existing techniques for training language models can be misaligned with the truth: if we train models with imitation learning, they may reproduce errors that humans make; if we train them to generate text that humans rate highly, they may…

To combat the potential misuse of Natural Language Generation (NLG) technology, a variety of algorithms have been developed for the detection of AI-generated texts. Traditionally, this task is treated as a binary classification problem.…

This paper presents two ways of dealing with scarce data in semantic decoding using N-Best speech recognition hypotheses. First, we learn features by using a deep learning architecture in which the weights for the unknown and known…

Audio-text models trained via contrastive learning offer a practical approach to perform audio classification through natural language prompts, such as "this is a sound of" followed by category names. In this work, we explore alternative…

Sentence compression reduces the length of text by removing non-essential content while preserving important facts and grammaticality. Unsupervised objective driven methods for sentence compression can be used to create customized models…

Self-supervised representation learning solves auxiliary prediction tasks (known as pretext tasks) without requiring labeled data to learn useful semantic representations. These pretext tasks are created solely using the input features,…

For sequence transduction tasks like speech recognition, a strong structured prior model encodes rich information about the target space, implicitly ruling out invalid sequences by assigning them low probability. In this work, we propose…

Few-shot classification (FSC) is challenging due to the scarcity of labeled training data (e.g. only one labeled data point per class). Meta-learning has shown to achieve promising results by learning to initialize a classification model…

In realistic open-set scenarios where labels of a part of testing data are totally unknown, when vision-language (VL) prompt learning methods encounter inputs related to unknown classes (i.e., not seen during training), they always predict…

Large language models have recently been shown to attain reasonable zero-shot generalization on a diverse set of tasks (Brown et al., 2020). It has been hypothesized that this is a consequence of implicit multitask learning in language…

Despite recent success in machine reading comprehension (MRC), learning high-quality MRC models still requires large-scale labeled training data, even using strong pre-trained language models (PLMs). The pre-training tasks for PLMs are not…

When pre-trained on large unsupervised textual corpora, language models are able to store and retrieve factual knowledge to some extent, making it possible to use them directly for zero-shot cloze-style question answering. However, storing…