Related papers: Zero-Shot Audio Classification with Factored Linea…
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,…
In this paper, we address zero-shot learning (ZSL), the problem of recognizing categories for which no labeled visual data are available during training. We focus on the transductive setting, in which unlabelled visual data from unseen…
Interpreting the decisions of deep learning models, including audio classifiers, is crucial for ensuring the transparency and trustworthiness of this technology. In this paper, we introduce LMAC-ZS (Listenable Maps for Audio Classifiers in…
Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker. Previous works have made progress on voice conversion with parallel training data and…
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…
Object recognition systems usually require fully complete manually labeled training data to train the classifier. In this paper, we study the problem of object recognition where the training samples are missing during the classifier…
Semantic segmentation, which aims to acquire a detailed understanding of images, is an essential issue in computer vision. However, in practical scenarios, new categories that are different from the categories in training usually appear.…
Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space between image and semantic representations. For years, among existing works, it has been the center task to learn the proper mapping matrices…
Zero-shot instance segmentation aims to detect and precisely segment objects of unseen categories without any training samples. Since the model is trained on seen categories, there is a strong bias that the model tends to classify all the…
Standard machine learning models for tagging and classifying acoustic signals cannot handle classes that were not seen during training. Zero-Shot (ZS) learning overcomes this restriction by predicting classes based on adaptable class…
Zero-Shot Learning (ZSL) aims to classify a test instance from an unseen category based on the training instances from seen categories, in which the gap between seen categories and unseen categories is generally bridged via visual-semantic…
Zero-shot learning (ZSL) aims to identify unseen classes with zero samples during training. Broadly speaking, present ZSL methods usually adopt class-level semantic labels and compare them with instance-level semantic predictions to infer…
Advances in deep learning have resulted in state-of-the-art performance for many audio classification tasks but, unlike humans, these systems traditionally require large amounts of data to make accurate predictions. Not every person or…
Masked language models like BERT can perform text classification in a zero-shot fashion by reformulating downstream tasks as text infilling. However, this approach is highly sensitive to the template used to prompt the model, yet…
Zero-shot learning transfers knowledge from seen classes to novel unseen classes to reduce human labor of labelling data for building new classifiers. Much effort on zero-shot learning however has focused on the standard multi-class…
Fine-grained image classification, which aims to distinguish images with subtle distinctions, is a challenging task due to two main issues: lack of sufficient training data for every class and difficulty in learning discriminative features…
Audio-visual generalized zero-shot learning is a rapidly advancing domain that seeks to understand the intricate relations between audio and visual cues within videos. The overarching goal is to leverage insights from seen classes to…
Generalised zero-shot learning (GZSL) methods aim to classify previously seen and unseen visual classes by leveraging the semantic information of those classes. In the context of GZSL, semantic information is non-visual data such as a text…
We study two foundational problems in audio language models: (1) how to design an audio tokenizer that can serve as an intermediate representation for both understanding and generation; and (2) how to build an audio foundation model that…
Recent advances in using language models to obtain cross-modal audio-text representations have overcome the limitations of conventional training approaches that use predefined labels. This has allowed the community to make progress in tasks…