轻量CNN在跨域水下塑料检测中表现最佳，适合实际部署。
Domain-Robust Marine Plastic Detection Using Vision Models
- 用轻量级CNN和视觉变压器测试跨域鲁棒性，评估不同模型在新数据上的表现。
- MobileNetV2在跨域测试中达F1 0.97，所有微调模型精确率均超99%。
- 零样本模型各有优劣：CLIP更敏感但误报多，Gemini精度高但召回略低。
海洋塑料污染是紧迫的环境威胁，可靠的水下垃圾自动检测至关重要。然而，基于某一数据集训练的视觉系统在新图像上常因领域偏移而性能下降。本研究对多种模型进行跨域鲁棒性基准测试：在标注的水下数据集上训练卷积神经网络（MobileNetV2、ResNet-18、EfficientNet-B0）和视觉变换器（DeiT-Tiny、ViT-B16），并在来自不同来源的正样本与训练域负样本组成的平衡测试集上评估其表现。同时评估了两个零样本模型——CLIP ViT-L14 和 Google Gemini 2.0 Flash——利用预训练实现无需微调的分类。结果表明，轻量级 MobileNetV2 在跨域任务中表现最强（F1 0.97），优于更大模型。所有微调模型均达到约99%的高精确率，但召回率存在差异，显示对塑料实例的敏感性不一。零样本模型中，CLIP 召回率约80%但精确率仅约56%，易产生误报；而 Gemini 精确率约99%、召回率约81%，反之。错误分析揭示常见混淆因素包括珊瑚纹理、悬浮颗粒及镜面反光。总体而言，经监督训练的紧凑型CNN在跨域水下检测中具备良好泛化能力，而大型预训练视觉-语言模型则提供互补优势。
原文摘要 · Abstract (English)
Marine plastic pollution is a pressing environmental threat, making reliable automation for underwater debris detection essential. However, vision systems trained on one dataset often degrade on new imagery due to domain shift. This study benchmarks models for cross-domain robustness, training convolutional neural networks - CNNs (MobileNetV2, ResNet-18, EfficientNet-B0) and vision transformers (DeiT-Tiny, ViT-B16) on a labeled underwater dataset and then evaluates them on a balanced cross-domain test set built from plastic-positive images drawn from a different source and negatives from the training domain. Two zero-shot models were assessed, CLIP ViT-L14 and Google's Gemini 2.0 Flash, that leverage pretraining to classify images without fine-tuning. Results show the lightweight MobileNetV2 delivers the strongest cross-domain performance (F1 0.97), surpassing larger models. All fine-tuned models achieved high Precision (around 99%), but differ in Recall, indicating varying sensitivity to plastic instances. Zero-shot CLIP is comparatively sensitive (Recall around 80%) yet prone to false positives (Precision around 56%), whereas Gemini exhibits the inverse profile (Precision around 99%, Recall around 81%). Error analysis highlights recurring confusions with coral textures, suspended particulates, and specular glare. Overall, compact CNNs with supervised training can generalize effectively for cross-domain underwater detection, while large pretrained vision-language models provide complementary strengths.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。