# Advancing underwater acoustic target recognition via adaptive data pruning and smoothness-inducing regularization

arXiv: https://arxiv.org/abs/2304.11907 · HTML: https://mlsanity.com/paper/2304.11907/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 24 Apr 2023.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization](https://mlsanity.com/paper/1911.03437/) (2019)
- [Scaling Laws and Interpretability of Learning from Repeated Data](https://mlsanity.com/paper/2205.10487/) (2022)
- [Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method](https://mlsanity.com/paper/2101.08533/) (2021)
- [Integrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modeling](https://mlsanity.com/paper/1907.06639/) (2019)
- [Acoustic event detection for multiple overlapping similar sources](https://mlsanity.com/paper/1503.07150/) (2015)

## Built on by (most cited first, 2 of 2)

- [Advancing Robust Underwater Acoustic Target Recognition through Multi-task Learning and Multi-Gate Mixture-of-Experts](https://mlsanity.com/paper/2411.02787/) (2024)
- [DEMONet: Underwater Acoustic Target Recognition based on Multi-Expert Network and Cross-Temporal Variational Autoencoder](https://mlsanity.com/paper/2411.02758/) (2024)

## Abstract (arXiv)

Underwater acoustic recognition for ship-radiated signals has high practical application value due to the ability to recognize non-line-of-sight targets. However, due to the difficulty of data acquisition, the collected signals are scarce in quantity and mainly composed of mechanical periodic noise. According to the experiments, we observe that the repeatability of periodic signals leads to a double-descent phenomenon, which indicates a significant local bias toward repeated samples. To address this issue, we propose a strategy based on cross-entropy to prune excessively similar segments in training data. Furthermore, to compensate for the reduction of training data, we generate noisy samples and apply smoothness-inducing regularization based on KL divergence to mitigate overfitting. Experiments show that our proposed data pruning and regularization strategy can bring stable benefits and our framework significantly outperforms the state-of-the-art in low-resource scenarios.