虚假关系
计算机科学
背景(考古学)
事件(粒子物理)
班级(哲学)
混淆
帧(网络)
人工智能
基线(sea)
机器学习
统计
数学
物理
地质学
古生物学
海洋学
生物
电信
量子力学
作者
Yifei Xin,Dongchao Yang,Fan Cui,Yujun Wang,Yuexian Zou
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2023-05-05
卷期号:: 1-5
被引量:3
标识
DOI:10.1109/icassp49357.2023.10096245
摘要
Existing weakly supervised sound event detection (WSSED) work has not explored both types of co-occurrences simultaneously, i.e., some sound events often co-occur, and their occurrences are usually accompanied by specific background sounds, so they would be inevitably entangled, causing misclassification and biased localization results with only clip-level supervision. To tackle this issue, we first establish a structural causal model (SCM) to reveal that the context is the main cause of co-occurrence confounders that mislead the model to learn spurious correlations between frames and clip-level labels. Based on the causal analysis, we propose a causal intervention (CI) method for WSSED to remove the negative impact of co-occurrence confounders by iteratively accumulating every possible context of each class and then re-projecting the contexts to the frame-level features for making the event boundary clearer. Experiments show that our method effectively improves the performance on multiple datasets and can generalize to various baseline models.
科研通智能强力驱动
Strongly Powered by AbleSci AI