Related papers: Enhancing Zero-shot Audio Classification using Sou…

Large audio-language models (LALMs) exhibit strong zero-shot capabilities in multiple downstream tasks, such as audio question answering (AQA) and abstract reasoning; however, these models still lag behind specialized models for certain…

Most existing methods for audio classification assume that the vocabulary of audio classes to be classified is fixed. When novel (unseen) audio classes appear, audio classification systems need to be retrained with abundant labeled samples…

Recently, zero-shot learning (ZSL) has received increasing interest. The key idea underpinning existing ZSL approaches is to exploit knowledge transfer via an intermediate-level semantic representation which is assumed to be shared between…

We study the problem of recognizing visual entities from the textual descriptions of their classes. Specifically, given birds' images with free-text descriptions of their species, we learn to classify images of previously-unseen species…

As an important and challenging problem in computer vision, zero-shot learning (ZSL) aims at automatically recognizing the instances from unseen object classes without training data. To address this problem, ZSL is usually carried out in…

Our objective is to generate Audio Descriptions (ADs) for both movies and TV series in a training-free manner. We use the power of off-the-shelf Visual-Language Models (VLMs) and Large Language Models (LLMs), and develop visual and text…

Vision-Language Models for remote sensing have shown promising uses thanks to their extensive pretraining. However, their conventional usage in zero-shot scene classification methods still involves dividing large images into patches and…

Automatic sound classification has a wide range of applications in machine listening, enabling context-aware sound processing and understanding. This paper explores methodologies for automatically classifying heterogeneous sounds…

Recent progress in self-training, self-supervised pretraining and unsupervised learning enabled well performing speech recognition systems without any labeled data. However, in many cases there is labeled data available for related…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

In a traditional setting, classifiers are trained to approximate a target function $f:X \rightarrow Y$ where at least a sample for each $y \in Y$ is presented to the training algorithm. In a zero-shot setting we have a subset of the labels…

Insufficient or even unavailable training data of emerging classes is a big challenge of many classification tasks, including text classification. Recognising text documents of classes that have never been seen in the learning stage,…

Few-shot learning has emerged as a powerful paradigm for training models with limited labeled data, addressing challenges in scenarios where large-scale annotation is impractical. While extensive research has been conducted in the image…

This study is part of the debate on the efficiency of large versus small language models for text classification by prompting.We assess the performance of small language models in zero-shot text classification, challenging the prevailing…

Multi-label zero-shot classification aims to predict multiple unseen class labels for an input image. It is more challenging than its single-label counterpart. On one hand, the unconstrained number of labels assigned to each image makes the…

Acoustic scene classification (ASC) predominantly relies on supervised approaches. However, acquiring labeled data for training ASC models is often costly and time-consuming. Recently, self-supervised learning (SSL) has emerged as a…

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…

Language models built using semi-supervised machine learning on large corpora of natural language have very quickly enveloped the fields of natural language generation and understanding. In this paper we apply a zero-shot approach…

Zero-shot learning (ZSL) aims to predict unseen classes whose samples have never appeared during training. One of the most effective and widely used semantic information for zero-shot image classification are attributes which are…

Despite significant progress in object categorization, in recent years, a number of important challenges remain; mainly, the ability to learn from limited labeled data and to recognize object classes within large, potentially open, set of…