Scholarlink

<p>Automated wildlife monitoring from aerial imagery is vital for conservation but remains limited by two persistent challenges: the difficulty of detecting small, rare species and the high cost of large-scale expert annotation. Prairie dogs exemplify this problem–they are ecologically important yet appear tiny, sparsely distributed, and visually indistinct from their surroundings, posing a severe challenge for conventional detection models. To overcome these limitations, we present <b>RareSpot+</b>, a detection framework that integrates multi-scale consistency learning, context-aware augmentation, and geospatially guided active learning to address these issues. A novel multi-scale consistency loss aligns intermediate feature maps across detection heads, enhancing localization of small (<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\sim \)</EquationSource> <EquationSource Format="MATHML"><math> <mo>∼</mo> </math></EquationSource> </InlineEquation> 30 pixels wide) objects without architectural changes, while context-aware augmentation improves robustness by synthesizing hard, ecologically plausible examples. A geospatial active learning module exploits domain-specific spatial priors linking prairie dogs and burrows, together with test-time augmentation and a meta-uncertainty model, to reduce redundant labeling. On a 2&#xa0;<InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\hbox {km}^2\)</EquationSource> <EquationSource Format="MATHML"><math> <msup> <mtext>km</mtext> <mn>2</mn> </msup> </math></EquationSource> </InlineEquation> aerial dataset, RareSpot+ improves detection over the baseline mAP@50 by +35.2% (absolute +0.13). Cross-dataset tests on HerdNet, AED, and several other wildlife benchmarks demonstrate robust detector-level transferability. The active learning module further boosts prairie dog AP by 10.7% using an annotation budget of just 1.7% of the unlabeled tiles. Beyond detection, RareSpot+ enables spatial ecological analyses such as clustering and co-occurrence, linking vision-based detection with quantitative ecology.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

RareSpot+: A Benchmark, Model, and Active Learning Framework for Small and Rare Wildlife in Aerial Imagery

  • 期刊论文

  • 发表日期：

    2026年7月31日

查看全文
  • Bowen Zhang,
  • Jesse T. Boulerice,
  • Charvi Mendiratta,
  • Nikhil Kuniyil,
  • Satish Kumar,
  • Hila Shamon,
  • B. S. Manjunath

摘要

Automated wildlife monitoring from aerial imagery is vital for conservation but remains limited by two persistent challenges: the difficulty of detecting small, rare species and the high cost of large-scale expert annotation. Prairie dogs exemplify this problem–they are ecologically important yet appear tiny, sparsely distributed, and visually indistinct from their surroundings, posing a severe challenge for conventional detection models. To overcome these limitations, we present RareSpot+, a detection framework that integrates multi-scale consistency learning, context-aware augmentation, and geospatially guided active learning to address these issues. A novel multi-scale consistency loss aligns intermediate feature maps across detection heads, enhancing localization of small ( \(\sim \) ∼ 30 pixels wide) objects without architectural changes, while context-aware augmentation improves robustness by synthesizing hard, ecologically plausible examples. A geospatial active learning module exploits domain-specific spatial priors linking prairie dogs and burrows, together with test-time augmentation and a meta-uncertainty model, to reduce redundant labeling. On a 2  \(\hbox {km}^2\) km 2 aerial dataset, RareSpot+ improves detection over the baseline mAP@50 by +35.2% (absolute +0.13). Cross-dataset tests on HerdNet, AED, and several other wildlife benchmarks demonstrate robust detector-level transferability. The active learning module further boosts prairie dog AP by 10.7% using an annotation budget of just 1.7% of the unlabeled tiles. Beyond detection, RareSpot+ enables spatial ecological analyses such as clustering and co-occurrence, linking vision-based detection with quantitative ecology.