相关论文: SemSup-XC: Semantic Supervision for Zero and Few-s…

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…

Contrastive Language-Image Pre-training (CLIP) provides a foundation model by integrating natural language into visual concepts, enabling zero-shot recognition on downstream tasks. It is usually expected that satisfactory overall accuracy…

Self-attention is of vital importance in semantic segmentation as it enables modeling of long-range context, which translates into improved performance. We argue that it is equally important to model short-range context, especially to…

This paper develops the MUFIN technique for extreme classification (XC) tasks with millions of labels where datapoints and labels are endowed with visual and textual descriptors. Applications of MUFIN to product-to-product recommendation…

Zero-shot classification of image scenes which can recognize the image scenes that are not seen in the training stage holds great promise of lowering the dependence on large numbers of labeled samples. To address the zero-shot image scene…

This work investigates the use of natural language to enable zero-shot model adaptation to new tasks. We use text and metadata from social commenting platforms as a source for a simple pretraining task. We then provide the language model…

Zero-shot learning strives to classify unseen categories for which no data is available during training. In the generalized variant, the test samples can further belong to seen or unseen categories. The state-of-the-art relies on Generative…

Event cameras excel in capturing high-contrast scenes and dynamic objects, offering a significant advantage over traditional frame-based cameras. Despite active research into leveraging event cameras for semantic segmentation, generating…

The successful application of deep learning to many visual recognition tasks relies heavily on the availability of a large amount of labeled data which is usually expensive to obtain. The few-shot learning problem has attracted increasing…

Few-shot learning aims at rapidly adapting to novel categories with only a handful of samples at test time, which has been predominantly tackled with the idea of meta-learning. However, meta-learning approaches essentially learn across a…

The extreme multi-label classification (XMC) task aims at tagging content with a subset of labels from an extremely large label set. The label vocabulary is typically defined in advance by domain experts and assumed to capture all necessary…

Recent deep learning-based methods for lossy image compression achieve competitive rate-distortion performance through extensive end-to-end training and advanced architectures. However, emerging applications increasingly prioritize semantic…

Time series classification is an important problem in data mining with several applications in different domains. Because time series data are usually high dimensional, dimensionality reduction techniques have been proposed as an efficient…

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…

Few-shot classification aims to learn a model that can generalize well to new tasks when only a few labeled samples are available. To make use of unlabeled data that are more abundantly available in real applications, Ren et al.…

zero-shot learning is an essential part of computer vision. As a classical downstream task, zero-shot semantic segmentation has been studied because of its applicant value. One of the popular zero-shot semantic segmentation methods is based…

Most previous few-shot learning algorithms are based on meta-training with fake few-shot tasks as training samples, where large labeled base classes are required. The trained model is also limited by the type of tasks. In this paper we…

Contrastive self-supervised learning methods learn to map data points such as images into non-parametric representation space without requiring labels. While highly successful, current methods require a large amount of data in the training…

The performance of vision-language models (VLMs), such as CLIP, in visual classification tasks, has been enhanced by leveraging semantic knowledge from large language models (LLMs), including GPT. Recent studies have shown that in zero-shot…

The claim matching (CM) task can benefit an automated fact-checking pipeline by putting together claims that can be resolved with the same fact-check. In this work, we are the first to explore zero-shot and few-shot learning approaches to…