Related papers: Weakly Supervised Source-Specific Sound Level Esti…

Audio-Visual Semantic Segmentation (AVSS) aligns audio and video at the pixel level but requires costly per-frame annotations. We introduce Weakly Supervised Audio-Visual Semantic Segmentation (WSAVSS), which uses only video-level labels to…

In practical machine learning applications, it is often challenging to assign accurate labels to data, and increasing the number of labeled instances is often limited. In such cases, Weakly Supervised Learning (WSL), which enables training…

Recent progress in speech recognition has relied on models trained on vast amounts of labeled data. However, classroom Automatic Speech Recognition (ASR) faces the real-world challenge of abundant weak transcripts paired with only a small…

Scarcity of pixel-level labels is a significant challenge in practical scenarios. In specific domains like industrial smoke, acquiring such detailed annotations is particularly difficult and often requires expert knowledge. To alleviate…

Visual sound source separation aims at identifying sound components from a given sound mixture with the presence of visual cues. Prior works have demonstrated impressive results, but with the expense of large multi-stage architectures and…

Weakly supervised semantic segmentation (WSSS) aims at learning a semantic segmentation model with only image-level tags. Despite intensive research on deep learning approaches over a decade, there is still a significant performance gap…

Current state-of-the-art methods for object detection rely on annotated bounding boxes of large data sets for training. However, obtaining such annotations is expensive and can require up to hundreds of hours of manual labor. This poses a…

Many datasets and approaches in ambient sound analysis use weakly labeled data.Weak labels are employed because annotating every data sample with a strong label is too expensive.Yet, their impact on the performance in comparison to strong…

Weakly-supervised semantic segmentation (WSSS) with image-level labels has been widely studied to relieve the annotation burden of the traditional segmentation task. In this paper, we show that existing fully-annotated base categories can…

The method of location and spectral estimation of weak signals on a noise background is being considered. The method is based on the optimized on order and noise dispersion autoregressive model of a sought signal. A new approach of model…

Weak supervision (WS) is a rich set of techniques that produce pseudolabels by aggregating easily obtained but potentially noisy label estimates from a variety of sources. WS is theoretically well understood for binary classification, where…

In noisy label learning, estimating noisy class posteriors plays a fundamental role for developing consistent classifiers, as it forms the basis for estimating clean class posteriors and the transition matrix. Existing methods typically…

In this paper, we study the performance of few-shot learning, specifically meta learning empowered few-shot relation networks, over supervised deep learning and conventional machine learning approaches in the problem of Sound Source…

One of the most time-consuming tasks for developers is the comprehension of new code bases. An effective approach to aid this process is to label source code files with meaningful annotations, which can help developers understand the…

Immersive communication has made significant advancements, especially with the release of the codec for Immersive Voice and Audio Services. Aiming at its further realization, the DCASE 2025 Challenge has recently introduced a task for…

Point cloud analysis has received much attention recently; and segmentation is one of the most important tasks. The success of existing approaches is attributed to deep network design and large amount of labelled training data, where the…

Existing methods for large-scale point cloud semantic segmentation require expensive, tedious and error-prone manual point-wise annotations. Intuitively, weakly supervised training is a direct solution to reduce the cost of labeling.…

Data-based and learning-based sound source localization (SSL) has shown promising results in challenging conditions, and is commonly set as a classification or a regression problem. Regression-based approaches have certain advantages over…

Weakly Labelled learning has garnered lot of attention in recent years due to its potential to scale Sound Event Detection (SED) and is formulated as Multiple Instance Learning (MIL) problem. This paper proposes a Multi-Task Learning (MTL)…

This letter proposes a new approach to improve the accuracy of the Energy-based source localization methods in urban acoustic scenes. The proposed acoustic energy sensing flow estimation (ESFE) uses the sensors signal nonstationarity degree…