# Class-Incremental Learning for Multi-Label Audio Classification

arXiv: https://arxiv.org/abs/2401.04447 · HTML: https://mlsanity.com/paper/2401.04447/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jan 2024.

## Built on by (most cited first, 6 of 6)

- [A Comprehensive Review of Multimodal Large Language Models: Performance and Challenges Across Different Tasks](https://mlsanity.com/paper/2408.01319/) (2024)
- [Characterizing Continual Learning Scenarios and Strategies for Audio Analysis](https://mlsanity.com/paper/2407.00465/) (2024)
- [DREAM: Domain-agnostic Reverse Engineering Attributes of Black-box Model](https://mlsanity.com/paper/2412.05842/) (2024)
- [TAIL: Text-Audio Incremental Learning](https://mlsanity.com/paper/2503.04258/) (2025)
- [Traceback Translators Against Forgetting in Continual Fake Speech Detection](https://mlsanity.com/paper/2607.12569/) (2026)
- [Investigating catastrophic forgetting in sound event classification](https://mlsanity.com/paper/2609.11447/) (2026)

## Abstract (arXiv)

In this paper, we propose a method for class-incremental learning of potentially overlapping sounds for solving a sequence of multi-label audio classification tasks. We design an incremental learner that learns new classes independently of the old classes. To preserve knowledge about the old classes, we propose a cosine similarity-based distillation loss that minimizes discrepancy in the feature representations of subsequent learners, and use it along with a Kullback-Leibler divergence-based distillation loss that minimizes discrepancy in their respective outputs. Experiments are performed on a dataset with 50 sound classes, with an initial classification task containing 30 base classes and 4 incremental phases of 5 classes each. After each phase, the system is tested for multi-label classification with the entire set of classes learned so far. The proposed method obtains an average F1-score of 40.9% over the five phases, ranging from 45.2% in phase 0 on 30 classes, to 36.3% in phase 4 on 50 classes. Average performance degradation over incremental phases is only 0.7 percentage points from the initial F1-score of 45.2%.