轻量级网络BarkNet-Lite实现高精度树种识别，适配手机端实时推理。
BarkNet-Lite: A Lightweight Texture and Colour Network with the BarkBD Benchmark for Bark-Based Tree Species Recognition in Bangladesh
- 设计多尺度纹理与颜色并行路径，296万参数从零训练
- 在孟加拉国数据集上达96.64%准确率，接近大模型性能
- 模型可部署于手机，单图识别仅需15.34毫秒
树种识别支持森林清查与生物多样性监测，但依赖稀缺分类学专家。树皮全年可见且位于地表，现有研究多集中于温带植物及大型ImageNet预训练模型。本文填补两大空白：首先发布BarkBD数据集——包含14,258张未裁剪智能手机拍摄的孟加拉国20种本土树种图像，覆盖四个行政区和三种天气条件，采用固定分层划分；其次提出BarkNet-Lite，一个2.96M参数的轻量级网络，通过多尺度纹理路径与并行颜色感知路径实现从零训练。在五次种子实验下，其单图推理准确率达96.64±0.66%，距九个微调的ImageNet预训练骨干网络仅差2.3个百分点，且低于最小骨干网络标准差内。该模型在公开基准上表现优异（BarkVN-50为95.86%，BarkNet 1.0为92.85%）。经梯度加权类激活映射（Grad-CAM）验证，决策基于树皮结构而非背景。导出的单精度模型在普通智能手机上处理一张图像仅需15.34毫秒。
原文摘要 · Abstract (English)
Tree species recognition supports forest inventory and biodiversity monitoring but still depends on scarce taxonomic expertise. Bark is visible year-round at ground level, yet bark recognition has concentrated on temperate floras and on large ImageNet-pre-trained backbones. We address both gaps. First, we release BarkBD, a bark dataset for Bangladesh: 14,258 uncropped smartphone photographs of 20 native species across four districts and three weather conditions, with a fixed stratified split. Second, we propose BarkNet-Lite, a 2.96M-parameter network trained from random initialisation, pairing a multi-scale texture pathway with a parallel colour-aware pathway. Over five seeds it reaches 96.64+-0.66%accuracyunderstrict single-image inference, within 2.3 points of nine ImageNet-pre-trained backbones fine-tuned under an identical protocol and within one seed-level standard deviation of the smallest ofthem, andtransfers to public benchmarks (95.86% on BarkVN-50, 92.85% on BarkNet 1.0). Grad-CAM, validated by faithfulness and weight-randomisation checks, confirms its decisions rest on bark structure rather than background. The exported single-precision model classifies one photograph in 15.34ms on a commodity smartphone.
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。