Clustering and novel class recognition: evaluating bioacoustic deep learning feature extractors

• URL: http://arxiv.org/abs/2504.06710v1
• Date: Wed, 09 Apr 2025 09:13:18 GMT
• Title: Clustering and novel class recognition: evaluating bioacoustic deep learning feature extractors
• Authors: Vincent S. Kather, Burooj Ghani, Dan Stowell,
• Abstract summary: In computational bioacoustics, deep learning models are composed of feature extractors and classifiers.<n> benchmarking of classification scores provides insights into specific performance statistics.<n>It makes it impossible to compare models trained on very different taxonomic groups.
• Score: 3.320858630462999
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In computational bioacoustics, deep learning models are composed of feature extractors and classifiers. The feature extractors generate vector representations of the input sound segments, called embeddings, which can be input to a classifier. While benchmarking of classification scores provides insights into specific performance statistics, it is limited to species that are included in the models' training data. Furthermore, it makes it impossible to compare models trained on very different taxonomic groups. This paper aims to address this gap by analyzing the embeddings generated by the feature extractors of 15 bioacoustic models spanning a wide range of setups (model architectures, training data, training paradigms). We evaluated and compared different ways in which models structure embedding spaces through clustering and kNN classification, which allows us to focus our comparison on feature extractors independent of their classifiers. We believe that this approach lets us evaluate the adaptability and generalization potential of models going beyond the classes they were trained on.

Related papers

• A prototype-based model for set classification [2.0564549686015594]
  A common way to represent a set of vectors is to model them as linear subspaces. We present a prototype-based approach for learning on the manifold formed from such linear subspaces, the Grassmann manifold.
  arXiv  Detail & Related papers  (2024-08-25T04:29:18Z)
• Diffusion Models Beat GANs on Image Classification [37.70821298392606]
  Diffusion models have risen to prominence as a state-of-the-art method for image generation, denoising, inpainting, super-resolution, manipulation, etc. We present our findings that these embeddings are useful beyond the noise prediction task, as they contain discriminative information and can also be leveraged for classification. We find that with careful feature selection and pooling, diffusion models outperform comparable generative-discriminative methods for classification tasks.
  arXiv  Detail & Related papers  (2023-07-17T17:59:40Z)
• Towards Weakly-Supervised Hate Speech Classification Across Datasets [47.101942709219784]
  We show the effectiveness of a state-of-the-art weakly-supervised text classification model in various in-dataset and cross-dataset settings. We also conduct an in-depth quantitative and qualitative analysis of the source of poor generalizability of HS classification models.
  arXiv  Detail & Related papers  (2023-05-04T08:15:40Z)
• Anomaly Detection using Ensemble Classification and Evidence Theory [62.997667081978825]
  We present a novel approach for novel detection using ensemble classification and evidence theory. A pool selection strategy is presented to build a solid ensemble classifier. We use uncertainty for the anomaly detection approach.
  arXiv  Detail & Related papers  (2022-12-23T00:50:41Z)
• Learning Debiased and Disentangled Representations for Semantic Segmentation [52.35766945827972]
  We propose a model-agnostic and training scheme for semantic segmentation. By randomly eliminating certain class information in each training iteration, we effectively reduce feature dependencies among classes. Models trained with our approach demonstrate strong results on multiple semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-10-31T16:15:09Z)
• Visualizing Classifier Adjacency Relations: A Case Study in Speaker Verification and Voice Anti-Spoofing [72.4445825335561]
  We propose a simple method to derive 2D representation from detection scores produced by an arbitrary set of binary classifiers. Based upon rank correlations, our method facilitates a visual comparison of classifiers with arbitrary scores. While the approach is fully versatile and can be applied to any detection task, we demonstrate the method using scores produced by automatic speaker verification and voice anti-spoofing systems.
  arXiv  Detail & Related papers  (2021-06-11T13:03:33Z)
• No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data [78.69828864672978]
  A central challenge in training classification models in the real-world federated system is learning with non-IID data. We propose a novel and simple algorithm called Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated ssian mixture model. Experimental results demonstrate that CCVR state-of-the-art performance on popular federated learning benchmarks including CIFAR-10, CIFAR-100, and CINIC-10.
  arXiv  Detail & Related papers  (2021-06-09T12:02:29Z)
• Learning and Evaluating Representations for Deep One-class Classification [59.095144932794646]
  We present a two-stage framework for deep one-class classification. We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations. In experiments, we demonstrate state-of-the-art performance on visual domain one-class classification benchmarks.
  arXiv  Detail & Related papers  (2020-11-04T23:33:41Z)
• Network Classifiers Based on Social Learning [71.86764107527812]
  We propose a new way of combining independently trained classifiers over space and time. The proposed architecture is able to improve prediction performance over time with unlabeled data. We show that this strategy results in consistent learning with high probability, and it yields a robust structure against poorly trained classifiers.
  arXiv  Detail & Related papers  (2020-10-23T11:18:20Z)
• ALEX: Active Learning based Enhancement of a Model's Explainability [34.26945469627691]
  An active learning (AL) algorithm seeks to construct an effective classifier with a minimal number of labeled examples in a bootstrapping manner. In the era of data-driven learning, this is an important research direction to pursue. This paper describes our work-in-progress towards developing an AL selection function that in addition to model effectiveness also seeks to improve on the interpretability of a model during the bootstrapping steps.
  arXiv  Detail & Related papers  (2020-09-02T07:15:39Z)

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.