Related papers: Conformal Predictor for Improving Zero-shot Text C…
Large-scale cross-modal pre-training paradigms have recently shown ubiquitous success on a wide range of downstream tasks, e.g., zero-shot classification, retrieval and image captioning. However, their successes highly rely on the scale and…
Traditional computer vision models are trained to predict a fixed set of predefined categories. Recently, natural language has been shown to be a broader and richer source of supervision that provides finer descriptions to visual concepts…
We introduce compositional soft prompting (CSP), a parameter-efficient learning technique to improve the zero-shot compositionality of large-scale pretrained vision-language models (VLMs) like CLIP. We develop CSP for compositional…
Labeling large image datasets with attributes such as facial age or object type is tedious and sometimes infeasible. Supervised machine learning methods provide a highly accurate solution, but require manual labels which are often…
Text classification is fundamental in Natural Language Processing (NLP), and the advent of Large Language Models (LLMs) has revolutionized the field. This paper introduces an adaptable and reliable text classification paradigm, which…
In NLP, zero-shot classification (ZSC) is the task of assigning labels to textual data without any labeled examples for the target classes. A common method for ZSC is to fine-tune a language model on a Natural Language Inference (NLI)…
Conformal Prediction (CP) quantifies network uncertainty by building a small prediction set with a pre-defined probability that the correct class is within this set. In this study we tackle the problem of CP calibration based on a…
Recent advances in large language and vision-language models have enabled zero-shot inference, allowing models to solve new tasks without task-specific training. Various adaptation techniques such as prompt engineering, In-Context Learning…
Within textual emotion classification, the set of relevant labels depends on the domain and application scenario and might not be known at the time of model development. This conflicts with the classical paradigm of supervised learning in…
Recent work has demonstrated that pre-trained language models (PLMs) are zero-shot learners. However, most existing zero-shot methods involve heavy human engineering or complicated self-training pipelines, hindering their application to new…
Conformal Predictors (CP) are wrappers around ML models, providing error guarantees under weak assumptions on the data distribution. They are suitable for a wide range of problems, from classification and regression to anomaly detection.…
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…
In NLP, Zero-Shot Classification (ZSC) has become essential for enabling models to classify text into categories unseen during training, particularly in low-resource languages and domains where labeled data is scarce. While pretrained…
Contrastively trained text-image models have the remarkable ability to perform zero-shot classification, that is, classifying previously unseen images into categories that the model has never been explicitly trained to identify. However,…
Pre-trained language models (PLMs) have exhibited remarkable few-shot learning capabilities when provided a few examples in a natural language prompt as demonstrations of test instances, i.e., in-context learning. However, the performance…
As an algorithmic framework for learning to learn, meta-learning provides a promising solution for few-shot text classification. However, most existing research fail to give enough attention to class labels. Traditional basic framework…
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…
Recent advances in large pretrained language models have increased attention to zero-shot text classification. In particular, models finetuned on natural language inference datasets have been widely adopted as zero-shot classifiers due to…
In the era of foundation models, CLIP has emerged as a powerful tool for aligning text & visual modalities into a common embedding space. However, the alignment objective used to train CLIP often results in subpar visual features for…
With contrastive pre-training, sentence encoders are generally optimized to locate semantically similar samples closer to each other in their embedding spaces. In this work, we focus on the potential of their embedding spaces to be readily…