Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The paper introduces RareSpot+, a detection framework designed to improve automated wildlife monitoring of small, rare species in aerial imagery, specifically focusing on prairie dogs. It combines multi-scale consistency learning to enhance small object localization, context-aware augmentation for robustness, and geospatially guided active learning to reduce annotation costs. Experiments on a 2 km^2 aerial dataset demonstrate a +35.2% improvement in mAP@50 compared to baseline, with the active learning module further boosting performance by 14.5% using only 1.7% of the unlabeled data for annotation.
You can find tiny prairie dogs in massive aerial images with surprisingly little labeled data by exploiting ecological context and multi-scale feature consistency.
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 (approx. 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 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 14.5% 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.