paper-with-me

Papers

Self Training and Ensembling Frequency Dependent Networks with Coarse Prediction Pooling and Sound Event Bounding Boxes

2024-06-22 · Hyeonuk Nam, Deokki Min, Seungdeok Choi, Inhan Choi, Yong-Hwa Park

To tackle sound event detection (SED), we propose frequency dependent networks (FreDNets), which heavily leverage frequency-dependent methods. We apply frequency warping and FilterAugment, which are frequency-dependent data augmentation methods. The model architecture consists of 3 branches: audio teacher-student transformer (ATST) branch, BEATs branch and CNN branch including either partial dilated frequency dynamic convolution (PDFD conv) or squeeze-and-Excitation (SE) with time-frame frequency-wise SE (tfwSE). To train MAESTRO labels with coarse temporal resolution, we applied max pooling on prediction for the MAESTRO dataset. Using best ensemble model, we applied self training to obtain pseudo label from DESED weak set, unlabeled set and AudioSet. AudioSet pseudo labels, filtered to focus on high-confidence labels, are used to train on DESED dataset only. We used change-detection-based sound event bounding boxes (cSEBBs) as post processing for ensemble models on self training and submission models. The resulting FreDNet was ranked 2nd in DCASE 2024 Challenge Task 4.

📄 PDF Abstract BibTeX arXiv:2406.15725

Code (1)

frednam93/MDFD-SED pytorch

Tasks

Change DetectionData AugmentationEvent DetectionPseudo LabelSound Event Detection

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Focus 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Investigating Multi-Feature Selection and Ensembling for Audio Classification

2022-06-15 · Muhammad Turab, Teerath Kumar, Malika Bendechache, Takfarinas Saber

Deep Learning (DL) algorithms have shown impressive performance in diverse domains. Among them, audio has attracted many researchers over the last couple of decades due to some interesting patterns--particularly in class…

Audio ClassificationClassificationfeature selection

Domain Confusion with Self Ensembling for Unsupervised Adaptation

2018-10-10 · Jiawei Wang, Zhaoshui He, Chengjian Feng, Zhouping Zhu 외

Data collection and annotation are time-consuming in machine learning, expecially for large scale problem. A common approach for this problem is to transfer knowledge from a related labeled domain to a target one. There …

Domain AdaptationUnsupervised Domain Adaptation

Robust Self-Ensembling Network for Hyperspectral Image Classification

2021-04-08 · Yonghao Xu, Bo Du, Liangpei Zhang

Recent research has shown the great potential of deep learning algorithms in the hyperspectral image (HSI) classification task. Nevertheless, training these models usually requires a large amount of labeled data. Since t…

ClassificationGeneral ClassificationHyperspectral Image Classificationimage-classification+1

Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation

2019-09-02 · ICCV 2019 10 · Jaehoon Choi, Taekyung Kim, Changick Kim

Deep learning-based semantic segmentation methods have an intrinsic limitation that training a model requires a large amount of data with pixel-level annotations. To address this challenging issue, many researchers give …

Data AugmentationDomain AdaptationSegmentationSemantic Segmentation+1

Mean Embeddings with Test-Time Data Augmentation for Ensembling of Representations

2021-06-15 · Arsenii Ashukha, Andrei Atanov, Dmitry Vetrov

Averaging predictions over a set of models -- an ensemble -- is widely used to improve predictive performance and uncertainty estimation of deep learning models. At the same time, many machine learning systems, such as s…

Data AugmentationImage RetrievalLinear evaluationRecommendation Systems+1