AFA-Underwater: Dual-Path Adaptive Feature Augmentation for Few-Shot Deep-Sea Trash Detection

Guangdong Zhu, Li Zhang

Advances in Computer and Materials Scienc Research Vol. 5 / No. 1 / pp. 168-175 / January 5, 2026

DOI 10.70114/acmsr.2025.5.1.P168

Full Screen
PDF

Abstract

As marine pollution intensifies, developing efficient deep-sea garbage detection technologies has become increasingly urgent. However, deep-sea environments present two major challenges: (i) the scarcity of target samples (few-shot problem), which makes it difficult to train deep learning models effectively; and (ii) harsh underwater imaging conditions—such as poor illumination and scattering—that lead to object blurring and background confusion. To address these challenges, this paper proposes AFA-Underwater, a framework specifically designed for few-shot deep-sea garbage detection. The core of this framework is a dual-path Adaptive Feature Augmentation (AFA) module, which generates more robust class prototypes to effectively mitigate the “prototype shift” problem caused by underwater noise. In addition, we introduce a novel Tri-Path Aggregation (TPA) mechanism that jointly models the raw, common, and differential representations between support and query features, thereby alleviating base-class bias. Extensive experiments on the re-partitioned TrashCAN 1.0 dataset demonstrate that AFA-Underwater significantly outperforms existing FSOD methods under multiple few-shot settings, achieving a remarkable 14.4% improvement in novel-class mAP under the 10-shot scenario. The algorithm also shows strong generalization capability on the PASCAL VOC dataset.

Keywords

Few-Shot Object Detection / Deep-Sea Trash Detection / Meta-Learning.

2025 International Conference on Computer Science, Energy, Civil and Environmental Engineering

Full Text

Download PDF

More in This Issue

  1. 25 Hydrotalcite-Based Composite Photothermal Coupling Catalysts: Realizing Green and Efficient Synthesis of High-Value Hydrogen Peroxide pp. 25–31
  2. 32 Modeling of Protoplanetary Disks Based on Radmc-3D pp. 32–39
  3. 11 Late Pleistocene Paleoclimate Oscillations in the Northeast Tarim Basin: Insights from Multi-Proxy Lacustrine Sediment Analysis (72-51 ka B.P.) pp. 11–24
  4. 1 Research on Ship Path Planning Based on Improved Whale Optimization Algorithm pp. 1–10
Full Issue

Cite This Article