Saved in:
Bibliographic Details
Main Authors: Fan, Zexia, Chen, Yu, Zhang, Qiquan, Chen, Kainan, Qian, Xinyuan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.18335
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918305427619840
author Fan, Zexia
Chen, Yu
Zhang, Qiquan
Chen, Kainan
Qian, Xinyuan
author_facet Fan, Zexia
Chen, Yu
Zhang, Qiquan
Chen, Kainan
Qian, Xinyuan
contents Sound source localization (SSL) demonstrates remarkable results in controlled settings but struggles in real-world deployment due to dual imbalance challenges: intra-task imbalance arising from long-tailed direction-of-arrival (DoA) distributions, and inter-task imbalance induced by cross-task skews and overlaps. These often lead to catastrophic forgetting, significantly degrading the localization accuracy. To mitigate these issues, we propose a unified framework with two key innovations. Specifically, we design a GCC-PHAT-based data augmentation (GDA) method that leverages peak characteristics to alleviate intra-task distribution skews. We also propose an Analytic dynamic imbalance rectifier (ADIR) with task-adaption regularization, which enables analytic updates that adapt to inter-task dynamics. On the SSLR benchmark, our proposal achieves state-of-the-art (SoTA) results of 89.0% accuracy, 5.3° mean absolute error, and 1.6 backward transfer, demonstrating robustness to evolving imbalances without exemplar storage.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18335
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Analytic Incremental Learning For Sound Source Localization With Imbalance Rectification
Fan, Zexia
Chen, Yu
Zhang, Qiquan
Chen, Kainan
Qian, Xinyuan
Sound
Artificial Intelligence
Sound source localization (SSL) demonstrates remarkable results in controlled settings but struggles in real-world deployment due to dual imbalance challenges: intra-task imbalance arising from long-tailed direction-of-arrival (DoA) distributions, and inter-task imbalance induced by cross-task skews and overlaps. These often lead to catastrophic forgetting, significantly degrading the localization accuracy. To mitigate these issues, we propose a unified framework with two key innovations. Specifically, we design a GCC-PHAT-based data augmentation (GDA) method that leverages peak characteristics to alleviate intra-task distribution skews. We also propose an Analytic dynamic imbalance rectifier (ADIR) with task-adaption regularization, which enables analytic updates that adapt to inter-task dynamics. On the SSLR benchmark, our proposal achieves state-of-the-art (SoTA) results of 89.0% accuracy, 5.3° mean absolute error, and 1.6 backward transfer, demonstrating robustness to evolving imbalances without exemplar storage.
title Analytic Incremental Learning For Sound Source Localization With Imbalance Rectification
topic Sound
Artificial Intelligence
url https://arxiv.org/abs/2601.18335