Related papers: Fully Few-shot Class-incremental Audio Classificat…
Music classification has been one of the most popular tasks in the field of music information retrieval. With the development of deep learning models, the last decade has seen impressive improvements in a wide range of classification tasks.…
Large-scale sound recognition data sets typically consist of acoustic recordings obtained from multimedia libraries. As a consequence, modalities other than audio can often be exploited to improve the outputs of models designed for…
Few-shot audio classification is an emerging topic that attracts more and more attention from the research community. Most existing work ignores the specificity of the form of the audio spectrogram and focuses largely on the embedding space…
We study few-shot acoustic event detection (AED) in this paper. Few-shot learning enables detection of new events with very limited labeled data. Compared to other research areas like computer vision, few-shot learning for audio recognition…
Few-shot learning is currently enjoying a considerable resurgence of interest, aided by the recent advance of deep learning. Contemporary approaches based on weight-generation scheme delivers a straightforward and flexible solution to the…
We propose regression networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each class. In high dimensional embedding…
Few-shot class incremental learning implies the model to learn new classes while retaining knowledge of previously learned classes with a small number of training instances. Existing frameworks typically freeze the parameters of the…
Few-shot Learning has been studied to mimic human visual capabilities and learn effective models without the need of exhaustive human annotation. Even though the idea of meta-learning for adaptation has dominated the few-shot learning…
State of the art (SOTA) few-shot learning (FSL) methods suffer significant performance drop in the presence of domain differences between source and target datasets. The strong discrimination ability on the source dataset does not…
Few-shot instance segmentation methods are promising when labeled training data for novel classes is scarce. However, current approaches do not facilitate flexible addition of novel classes. They also require that examples of each class are…
Many recent works on deep speaker embeddings train their feature extraction networks on large classification tasks, distinguishing between all speakers in a training set. Empirically, this has been shown to produce speaker-discriminative…
Few-shot learning aims to learn a classifier using a few labelled instances for each class. Metric-learning approaches for few-shot learning embed instances into a high-dimensional space and conduct classification based on distances among…
Deep learning techniques for separating audio into different sound sources face several challenges. Standard architectures require training separate models for different types of audio sources. Although some universal separators employ a…
Despite deep convolutional neural networks achieved impressive progress in medical image computing and analysis, its paradigm of supervised learning demands a large number of annotations for training to avoid overfitting and achieving…
An old-school recipe for training a classifier is to (i) learn a good feature extractor and (ii) optimize a linear layer atop. When only a handful of samples are available per category, as in Few-Shot Adaptation (FSA), data are insufficient…
Aiming to incrementally learn new classes with only few samples while preserving the knowledge of base (old) classes, few-shot class-incremental learning (FSCIL) faces several challenges, such as overfitting and catastrophic forgetting.…
Learning with limited data is a key challenge for visual recognition. Many few-shot learning methods address this challenge by learning an instance embedding function from seen classes and apply the function to instances from unseen classes…
The base learners and labeled samples (shots) in an ensemble few-shot classifier greatly affect the model performance. When the performance is not satisfactory, it is usually difficult to understand the underlying causes and make…
Feature representations derived from models pre-trained on large-scale datasets have shown their generalizability on a variety of audio analysis tasks. Despite this generalizability, however, task-specific features can outperform if…
Few-shot learning (FSL) aims to learn models that generalize to novel classes with limited training samples. Recent works advance FSL towards a scenario where unlabeled examples are also available and propose semi-supervised FSL methods.…