Histogram-based Parameter-efficient Tuning for Passive and Active Sonar Classification

arXiv:2504.15214v3 Announce Type: replace Abstract: Parameter-efficient transfer learning (PETL) methods adapt large artificial neural networks to downstream tasks without fine-tuning the entire model. However, existing additive methods, such as adapters, sometimes struggle to capture distributional shifts in intermediate feature embeddings. We propose a novel histogram-based parameter-efficient tuning (HPT) technique that captures the statistics of the target domain and modulates the embeddings. Experimental results on three downstream passive sonar datasets (ShipsEar, DeepShip, Vessel Type Underwater Acoustic Data (VTUAD)) demonstrate that HPT outperforms conventional adapters. Notably, HPT achieves 91.8% vs. 89.8% accuracy on VTUAD. For active sonar imagery (Watertank, Turntable), HPT is competitive with other PETL methods. Furthermore, HPT yields feature representations closer to those of fully fine-tuned models. Overall, HPT balances parameter savings and provides a distribution-aware alternative to existing adapters and shows a promising direction for transfer learning in resource-constrained environments. The code is publicly available: https://github.com/Advanced-Vision-and-Learning-Lab/HLAST_DeepShip_ParameterEfficient.

Related

• TeRA: Vector-based Random Tensor Network for High-Rank Adaptation of Large Language Models
• PiCa: Parameter-Efficient Fine-Tuning with Column Space Projection
• Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuning
• PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention
• Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models
• A Parameter-Efficient Transfer Learning Approach through Multitask Prompt Distillation and Decomposition for Clinical NLP

Source: arXiv cs.LG | 2026-04-20