Audio Tagging by Cross Filtering Noisy Labels

• URL: http://arxiv.org/abs/2007.08165v1
• Date: Thu, 16 Jul 2020 07:55:04 GMT
• Title: Audio Tagging by Cross Filtering Noisy Labels
• Authors: Boqing Zhu, Kele Xu, Qiuqiang Kong, Huaimin Wang, Yuxing Peng
• Abstract summary: We present a novel framework, named CrossFilter, to combat the noisy labels problem for audio tagging. Our method achieves state-of-the-art performance and even surpasses the ensemble models.
• Score: 26.14064793686316
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High quality labeled datasets have allowed deep learning to achieve impressive results on many sound analysis tasks. Yet, it is labor-intensive to accurately annotate large amount of audio data, and the dataset may contain noisy labels in the practical settings. Meanwhile, the deep neural networks are susceptive to those incorrect labeled data because of their outstanding memorization ability. In this paper, we present a novel framework, named CrossFilter, to combat the noisy labels problem for audio tagging. Multiple representations (such as, Logmel and MFCC) are used as the input of our framework for providing more complementary information of the audio. Then, though the cooperation and interaction of two neural networks, we divide the dataset into curated and noisy subsets by incrementally pick out the possibly correctly labeled data from the noisy data. Moreover, our approach leverages the multi-task learning on curated and noisy subsets with different loss function to fully utilize the entire dataset. The noisy-robust loss function is employed to alleviate the adverse effects of incorrect labels. On both the audio tagging datasets FSDKaggle2018 and FSDKaggle2019, empirical results demonstrate the performance improvement compared with other competing approaches. On FSDKaggle2018 dataset, our method achieves state-of-the-art performance and even surpasses the ensemble models.

Related papers

• Tackling Noisy Clients in Federated Learning with End-to-end Label Correction [20.64304520865249]
  We propose a two-stage framework FedELC to tackle this complicated label noise issue. The first stage aims to guide the detection of noisy clients with higher label noise. The second stage aims to correct the labels of noisy clients' data via an end-to-end label correction framework.
  arXiv  Detail & Related papers  (2024-08-08T08:35:32Z)
• FedNoisy: Federated Noisy Label Learning Benchmark [53.73816587601204]
  Federated learning has gained popularity for distributed learning without aggregating sensitive data from clients. The distributed and isolated nature of data isolation may be complicated by data quality, making it more vulnerable to noisy labels. We serve the first standardized benchmark that can help researchers fully explore potential federated noisy settings.
  arXiv  Detail & Related papers  (2023-06-20T16:18:14Z)
• Inconsistency Ranking-based Noisy Label Detection for High-quality Data [11.844624139434867]
  This paper proposes an automatic noisy label detection (NLD) technique with inconsistency ranking for high-quality data. We investigate both inter-class and intra-class inconsistency ranking and compare several metric learning loss functions under different noise settings. Experimental results confirm that the proposed solution could increase both the efficient and effective cleaning of large-scale speaker recognition datasets.
  arXiv  Detail & Related papers  (2022-12-01T03:09:33Z)
• Representation Learning for the Automatic Indexing of Sound Effects Libraries [79.68916470119743]
  We show that a task-specific but dataset-independent representation can successfully address data issues such as class imbalance, inconsistent class labels, and insufficient dataset size. Detailed experimental results show the impact of metric learning approaches and different cross-dataset training methods on representational effectiveness.
  arXiv  Detail & Related papers  (2022-08-18T23:46:13Z)
• Tripartite: Tackle Noisy Labels by a More Precise Partition [21.582850128741022]
  We propose a Tripartite solution to partition training data more precisely into three subsets: hard, noisy, and clean. To minimize the harm of noisy labels but maximize the value of noisy label data, we apply a low-weight learning on hard data and a self-supervised learning on noisy label data without using the given labels.
  arXiv  Detail & Related papers  (2022-02-19T11:15:02Z)
• Addressing out-of-distribution label noise in webly-labelled data [8.625286650577134]
  Data gathering and annotation using a search engine is a simple alternative to generating a fully human-annotated dataset. Although web crawling is very time efficient, some of the retrieved images are unavoidably noisy. Design robust algorithms for training on noisy data gathered from the web is an important research perspective.
  arXiv  Detail & Related papers  (2021-10-26T13:38:50Z)
• Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations [54.400167806154535]
  Existing research on learning with noisy labels mainly focuses on synthetic label noise. This work presents two new benchmark datasets (CIFAR-10N, CIFAR-100N) We show that real-world noisy labels follow an instance-dependent pattern rather than the classically adopted class-dependent ones.
  arXiv  Detail & Related papers  (2021-10-22T22:42:11Z)
• Learning to Aggregate and Refine Noisy Labels for Visual Sentiment Analysis [69.48582264712854]
  We propose a robust learning method to perform robust visual sentiment analysis. Our method relies on an external memory to aggregate and filter noisy labels during training. We establish a benchmark for visual sentiment analysis with label noise using publicly available datasets.
  arXiv  Detail & Related papers  (2021-09-15T18:18:28Z)
• Searching for Robustness: Loss Learning for Noisy Classification Tasks [81.70914107917551]
  We parameterize a flexible family of loss functions using Taylors and apply evolutionary strategies to search for noise-robust losses in this space. The resulting white-box loss provides a simple and fast "plug-and-play" module that enables effective noise-robust learning in diverse downstream tasks.
  arXiv  Detail & Related papers  (2021-02-27T15:27:22Z)
• Co-Seg: An Image Segmentation Framework Against Label Corruption [8.219887855003648]
  Supervised deep learning performance is heavily tied to the availability of high-quality labels for training. We propose a novel framework, namely Co-Seg, to collaboratively train segmentation networks on datasets which include low-quality noisy labels. Our framework can be easily implemented in any segmentation algorithm to increase its robustness to noisy labels.
  arXiv  Detail & Related papers  (2021-01-31T20:01:40Z)
• Attention-Aware Noisy Label Learning for Image Classification [97.26664962498887]
  Deep convolutional neural networks (CNNs) learned on large-scale labeled samples have achieved remarkable progress in computer vision. The cheapest way to obtain a large body of labeled visual data is to crawl from websites with user-supplied labels, such as Flickr. This paper proposes the attention-aware noisy label learning approach to improve the discriminative capability of the network trained on datasets with potential label noise.
  arXiv  Detail & Related papers  (2020-09-30T15:45:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.