Related papers: UCIL: An Unsupervised Class Incremental Learning A…

For learning-based sound event localization and detection (SELD) methods, different acoustic environments in the training and test sets may result in large performance differences in the validation and evaluation stages. Different…

Sound event localization and detection (SELD) involves identifying the direction-of-arrival (DOA) and the event class. The SELD methods with a class-wise output format make the model predict activities of all sound event classes and…

This paper explores the potential of event cameras to enable continuous time reinforcement learning. We formalise this problem where a continuous stream of unsynchronised observations is used to produce a corresponding stream of output…

In this paper, we propose a temporal-frequential attention model for sound event detection (SED). Our network learns how to listen with two attention models: a temporal attention model and a frequential attention model. Proposed system…

Class-incremental learning (CIL) for endoscopic image analysis is crucial for real-world clinical applications, where diagnostic models should continuously adapt to evolving clinical data while retaining performance on previously learned…

Given a model well-trained with a large-scale base dataset, Few-Shot Class-Incremental Learning (FSCIL) aims at incrementally learning novel classes from a few labeled samples by avoiding overfitting, without catastrophically forgetting all…

In class incremental learning (CIL) a model must learn new classes in a sequential manner without forgetting old ones. However, conventional CIL methods consider a balanced distribution for each new task, which ignores the prevalence of…

In this paper we present our work on Task 1 Acoustic Scene Classi- fication and Task 3 Sound Event Detection in Real Life Recordings. Among our experiments we have low-level and high-level features, classifier optimization and other…

Domain incremental learning aims to adapt to a sequence of domains with access to only a small subset of data (i.e., memory) from previous domains. Various methods have been proposed for this problem, but it is still unclear how they are…

Many deep learning applications, like keyword spotting, require the incorporation of new concepts (classes) over time, referred to as Class Incremental Learning (CIL). The major challenge in CIL is catastrophic forgetting, i.e., preserving…

In traditional sound event localization and detection (SELD) tasks, the focus is typically on sound event detection (SED) and direction-of-arrival (DOA) estimation, but they fall short of providing full spatial information about the sound…

Sound event localization and detection (SELD) combines the identification of sound events with the corresponding directions of arrival (DOA). Recently, event-oriented track output formats have been adopted to solve this problem; however,…

Recently, an event-based end-to-end model (SEDT) has been proposed for sound event detection (SED) and achieves competitive performance. However, compared with the frame-based model, it requires more training data with temporal annotations…

We consider class incremental learning (CIL) problem, in which a learning agent continuously learns new classes from incrementally arriving training data batches and aims to predict well on all the classes learned so far. The main challenge…

The rehearsal strategy is widely used to alleviate the catastrophic forgetting problem in class incremental learning (CIL) by preserving limited exemplars from previous tasks. With imbalanced sample numbers between old and new classes, the…

We address the problem of self-supervised learning on discrete event sequences generated by real-world users. Self-supervised learning incorporates complex information from the raw data in low-dimensional fixed-length vector representations…

Some studies have revealed that contexts of scenes (e.g., "home," "office," and "cooking") are advantageous for sound event detection (SED). Mobile devices and sensing technologies give useful information on scenes for SED without the use…

In the acoustic scene classification (ASC) task, an acoustic scene consists of diverse sounds and is inferred by identifying combinations of distinct attributes among them. This study aims to extract and cluster these attributes effectively…

Deep learning approaches achieve state-of-the-art performance for classifying radiology images, but rely on large labelled datasets that require resource-intensive annotation by specialists. Both semi-supervised learning and active learning…

This paper outlines our approach to the 5th CLVision challenge at CVPR, which addresses the Class-Incremental with Repetition (CIR) scenario. In contrast to traditional class incremental learning, this novel setting introduces unique…