Related papers: HalluAudio: Hallucinating Frequency as Concepts fo…
Few-shot learning is a rapidly evolving area of research in machine learning where the goal is to classify unlabeled data with only one or "a few" labeled exemplary samples. Neural networks are typically trained to minimize a distance…
Thanks to the availability of powerful computing resources, big data and deep learning algorithms, we have made great progress on computer vision in the last few years. Computer vision systems begin to surpass humans in some tasks, such as…
In visual recognition tasks, few-shot learning requires the ability to learn object categories with few support examples. Its re-popularity in light of the deep learning development is mainly in image classification. This work focuses on…
Human intelligence is characterized by our ability to absorb and apply knowledge from the world around us, especially in rapidly acquiring new concepts from minimal examples, underpinned by prior knowledge. Few-shot learning (FSL) aims to…
Few-shot classification aims to adapt classifiers to novel classes with a few training samples. However, the insufficiency of training data may cause a biased estimation of feature distribution in a certain class. To alleviate this problem,…
Humans are able to learn to recognize new objects even from a few examples. In contrast, training deep-learning-based object detectors requires huge amounts of annotated data. To avoid the need to acquire and annotate these huge amounts of…
Few-shot image classification learns to recognize new categories from limited labelled data. Metric learning based approaches have been widely investigated, where a query sample is classified by finding the nearest prototype from the…
Automatic detection and classification of animal sounds has many applications in biodiversity monitoring and animal behaviour. In the past twenty years, the volume of digitised wildlife sound available has massively increased, and automatic…
Meta-learning offers a promising avenue for few-shot learning (FSL), enabling models to glean a generalizable feature embedding through episodic training on synthetic FSL tasks in a source domain. Yet, in practical scenarios where the…
Transductive Few-Shot learning has gained increased attention nowadays considering the cost of data annotations along with the increased accuracy provided by unlabelled samples in the domain of few shot. Especially in Few-Shot…
This work proposes a novel feature selection algorithm to classify Songs into different groups. Classification of musical content is often a non-trivial job and still relatively less explored area. The main idea conveyed in this article is…
Diffraction limit is manifested in the loss of high spatial frequency information that results from decay of evanescent waves. As a result, conventional far-field optics yields no information about an object's subwavelength features. Here…
Environmental sound classification (ESC) is a challenging problem due to the unstructured spatial-temporal relations that exist in the sound signals. Recently, many studies have focused on abstracting features from convolutional neural…
We show that the way inference is performed in few-shot segmentation tasks has a substantial effect on performances -- an aspect often overlooked in the literature in favor of the meta-learning paradigm. We introduce a transductive…
We study the computational phase transition in a multi-frequency group synchronization problem, where pairwise relative measurements of group elements are observed across multiple frequency channels and corrupted by Gaussian noise. Using…
Open-set few-shot hyperspectral image (HSI) classification aims to classify image pixels by using few labeled pixels per class, where the pixels to be classified may be not all from the classes that have been seen. To address the open-set…
Supervised learning methods can solve the given problem in the presence of a large set of labeled data. However, the acquisition of a dataset covering all the target classes typically requires manual labeling which is expensive and…
Environmental Sound Classification (ESC) is a rapidly evolving field that recently demonstrated the advantages of application of visual domain techniques to the audio-related tasks. Previous studies indicate that the domain-specific…
There has been significant research on developing pretrained transformer architectures for multimodal-to-text generation tasks. Albeit performance improvements, such models are frequently overparameterized, hence suffer from hallucination…
Single image-level annotations only correctly describe an often small subset of an image's content, particularly when complex real-world scenes are depicted. While this might be acceptable in many classification scenarios, it poses a…