通过视频帧扩充数据集，实现边缘端鹰类轻量分类
Lightweight Image Classification of Raptor Species for Edge Devices: Rare-Species Dataset Expansion via Video Frame Extraction, Knowledge Distillation, and TensorRT Deployment
- 用视频帧扩展数据集，显著提升稀有鹰种样本数
- 轻量模型在边缘设备上达313帧/秒，精度保留97.5%
- 数据扩充与教师模型微调是性能提升主因
针对风力涡轮机碰撞防护的实时边缘部署需求，研究轻量级鹰类物种分类。以参数量304M的DINOv2-L为教师模型，蒸馏出MobileNetV4、ViT-Small和EfficientNet-B0三个轻量学生模型。为减少近缘物种混淆，通过视频帧提取将数据集扩展至12,519张图像，其中斯泰勒海雕样本从463张增至2,050张。在视频级与源图像级分离的分组划分下，三模型集成在五次蒸馏种子中实现0.935±0.004的宏召回率（常规图像级分组为0.955），保留教师模型97.5%的宏召回率，参数量仅为八分之一。在1,258张独立测试图像子集上，白尾海雕识别召回率提升38.6个百分点，误判为斯泰勒海雕的比例由61%降至15%。EfficientNet-B0在NVIDIA Jetson Orin Nano上以TensorRT FP16部署，单图处理耗时3.19毫秒（含主机-设备传输），每秒313帧，与FP32结果99.95%一致。五种子对比显示，蒸馏（相比仅交叉熵）或更换教师模型（从DINOv2-L到DINOv3-L）均未带来明显集成性能提升，主要收益来自数据集扩展与教师模型微调。
原文摘要 · Abstract (English)
We investigate lightweight raptor-species classification for real-time edge deployment in wind-turbine collision mitigation. Using DINOv2-L (304M parameters) as a teacher, we distilled three lightweight students (MobileNetV4, ViT-Small, and EfficientNet-B0). To reduce confusion between closely related species, we expanded the dataset to 12,519 images, including an increase in Steller's Sea Eagle images from 463 to 2,050 via video-frame extraction. Under a group split that separates samples at the video- and source-image level to mitigate source leakage at that granularity, the three-student ensemble achieved a macro recall of 0.935 +/- 0.004 over five distillation seeds (0.955 on a conventional image-level split, retaining 97.5% of the teacher's macro recall) with roughly one-eighth as many parameters. On a subset of 1,258 images disjoint from the former training images, White-tailed Eagle recall improved by up to 38.6 percentage points, while the rate at which it was misclassified as the Steller's Sea Eagle decreased from 61% to 15% of errors. TensorRT FP16 deployment of EfficientNet-B0 on an NVIDIA Jetson Orin Nano achieved 3.19 ms/image including host-device transfer (313 images/s), with 99.95% argmax agreement with FP32. In five-seed controlled comparisons, neither distillation (versus CE-only) nor the change from a DINOv2-L to a DINOv3-L teacher yielded a clear ensemble-level improvement; the primary gains stem from the dataset expansion and teacher re-fine-tuning.
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。