Related papers: A Simple Zero-shot Prompt Weighting Technique to I…

Recently, zero-shot multi-label classification has garnered considerable attention for its capacity to operate predictions on unseen labels without human annotations. Nevertheless, prevailing approaches often use seen classes as imperfect…

Few-shot learning is a challenging problem since only a few examples are provided to recognize a new class. Several recent studies exploit additional semantic information, e.g. text embeddings of class names, to address the issue of rare…

While deep learning, including Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), has significantly advanced classification performance, its typical reliance on extensive annotated datasets presents a major obstacle in…

Zero-shot multi-label recognition (MLR) with Vision-Language Models (VLMs) faces significant challenges without training data, model tuning, or architectural modifications. Existing approaches require prompt tuning or architectural…

Classifying scanned documents is a challenging problem that involves image, layout, and text analysis for document understanding. Nevertheless, for certain benchmark datasets, notably RVL-CDIP, the state of the art is closing in to…

Multi-modal image-text models such as CLIP and LiT have demonstrated impressive performance on image classification benchmarks and their zero-shot generalization ability is particularly exciting. While the top-5 zero-shot accuracies of…

Estimating mutual information from text usually requires training a task-specific critic, which limits its use in low-data settings. We ask whether large language models can instead estimate pointwise mutual information zero-shot, using…

Current methods for few-shot fine-tuning of pretrained masked language models (PLMs) require carefully engineered prompts and verbalizers for each new task to convert examples into a cloze-format that the PLM can score. In this work, we…

Well-designed prompts can guide text-to-image models to generate amazing images. However, the performant prompts are often model-specific and misaligned with user input. Instead of laborious human engineering, we propose prompt adaptation,…

For downstream applications of vision-language pre-trained models, there has been significant interest in constructing effective prompts. Existing works on prompt engineering, which either require laborious manual designs or optimize the…

We demonstrate that co-training (Blum & Mitchell, 1998) can improve the performance of prompt-based learning by using unlabeled data. While prompting has emerged as a promising paradigm for few-shot and zero-shot learning, it is often…

Existing solutions to zero-shot text classification either conduct prompting with pre-trained language models, which is sensitive to the choices of templates, or rely on large-scale annotated data of relevant tasks for meta-tuning. In this…

Classifiers built upon vision-language models such as CLIP have shown remarkable zero-shot performance across a broad range of image classification tasks. Prior work has studied different ways of automatically creating descriptor sets for…

Vision-language models (VLMs) have demonstrated remarkable zero-shot performance across various classification tasks. Nonetheless, their reliance on hand-crafted text prompts for each task hinders efficient adaptation to new tasks. While…

Zero-shot domain-specific image classification is challenging in classifying real images without ground-truth in-domain training examples. Recent research involved knowledge from texts with a text-to-image model to generate in-domain…

Popular zero-shot models suffer due to artifacts inherited from pretraining. One particularly detrimental issue, caused by unbalanced web-scale pretraining data, is mismatched label distribution. Existing approaches that seek to repair the…

Developing effective prompts demands significant cognitive investment to generate reliable, high-quality responses from Large Language Models (LLMs). By deploying case-specific prompt engineering techniques that streamline frequently…

Prompt engineering is an essential technique for enhancing the abilities of large language models (LLMs) by providing explicit and specific instructions. It enables LLMs to excel in various tasks, such as arithmetic reasoning, question…

Node classification is a fundamental problem in information retrieval with many real-world applications, such as community detection in social networks, grouping articles published online and product categorization in e-commerce. Zero-shot…

The vision-language model has brought great improvement to few-shot industrial anomaly detection, which usually needs to design of hundreds of prompts through prompt engineering. For automated scenarios, we first use conventional prompt…