高效标签的水下物种分类:基于冻结基础模型嵌入的逻辑回归
Label-efficient underwater image classification with logistic regression on frozen foundation model embeddings
AI总结:
本文研究了在冻结基础模型嵌入上使用逻辑回归进行水下物种分类,证明在标签稀缺情况下,冻结表示在物种层面具有强线性可分性,无需深度学习训练或领域特定数据工程。
摘要:
自动化水下图像物种分类受限于专家标注成本,且监督模型训练于一个数据集 rarely 转移到新条件。我们研究了简单分类器在冻结基础模型嵌入上能否缩小这一差距。使用冻结 DINOv3 ViT-B/16 嵌入,无微调训练逻辑回归分类器并在 AQUA20 挑战 (20 种海洋物种) 上评估。在全监督下,逻辑回归达到 88.5% 的宏 F1,对比 ConvNeXt 的 88.9%,差距 0.4 个百分点,且在 20 种物种中超过监督基线 8 种。在标签稀缺情况下,每类 21 个标注样本 (约 6% 的训练标签),宏 F1 超过 80%。与端到端监督学习的接近平局表明,这些通用冻结表示在水下领域具有强线性可分性。我们的方法无需深度学习训练、领域特定数据工程或水下适应模型,建立了一个实用、可立即部署的标签高效海洋物种识别基线。所有结果均在 100 次随机种子初始化下的保留测试集上报告。这是一份初步报告;进一步评估和消融分析将随后发布。
英文摘要:
Underwater image classification is constrained by the cost of annotation and by the computational and methodological requirements of task-specific model development. We investigate whether frozen general-purpose foundation-model embeddings can reduce these requirements by extracting DINOv3 ViT-B/16 embeddings and training only a logistic regression classifier on the AQUA20 benchmark. We evaluate the approach across a range of annotation budgets, a repeated 80% training-subsample evaluation, and a full-training refit. With only 13 labelled images per category, corresponding to approximately 4% of the benchmark's official training partition, mean macro F1 reaches 81.8%; with 144 images per category it reaches 88.5%, compared to the published fully supervised ConvNeXt point estimate of 88.9% obtained with the complete training set (benchmark results reported without run-to-run variability). Using all official training labels, macro F1 reaches 91.5% (bootstrap 95% CI: 89.0-93.7%). Sensitivity analyses show that the main findings remain stable across ordinary downstream implementation choices, and persist after removing duplicate and near-duplicate test images identified in an audit of the official split. Preliminary evaluation on a second dataset suggests that overall performance level and the shape of the label efficiency curve are not unique to the AQUA20 dataset. Because the DINOv3 backbone remains frozen and only the downstream classifier is fitted, the approach avoids task-specific neural-network training and can be executed on commodity hardware. These findings establish linear classification on frozen foundation-model embeddings as a practical baseline for label-efficient underwater image classification.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。