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

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

URL: http://arxiv.org/abs/2604.20000v1
Date: Tue, 21 Apr 2026 21:18:02 GMT
Title: RareSpot+: A Benchmark, Model, and Active Learning Framework for Small and Rare Wildlife in Aerial Imagery
Abstract summary: RareSpot+ is a detection framework that integrates multi-scale consistency learning, context-aware augmentation, and geospatially guided active learning.<n>On a 2 km2 aerial dataset, RareSpot+ improves detection over the baseline mAP@50 by +35.2% (absolute +0.13).<n>The active learning module further boosts prairie dog AP by 14.5% using an annotation budget of just 1.7% of the unlabeled tiles.
Score: 9.37940568498261
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
Abstract: 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.

Related papers

Enhancing Hazy Wildlife Imagery: AnimalHaze3k and IncepDehazeGan [0.0]
AnimalHaze3k is a synthetic hazy dataset of 3,477 images generated from 1,159 clear wildlife photographs.<n>Our novel IncepDehazeGan architecture combines inception blocks with residual skip connections in a GAN framework.<n>When applied to downstream detection tasks, dehazed images improved YOLOv11 detection mAP by 112% and IoU by 67%.
arXiv Detail & Related papers (2026-04-17T17:46:32Z)
Weakly supervised framework for wildlife detection and counting in challenging Arctic environments: a case study on caribou (Rangifer tarandus) [0.0]
We propose a weakly supervised patch-level pretraining based on a detection network's architecture.<n>This dataset includes five caribou herds distributed across Alaska.
arXiv Detail & Related papers (2026-01-26T19:02:18Z)
RareSpot: Spotting Small and Rare Wildlife in Aerial Imagery with Multi-Scale Consistency and Context-Aware Augmentation [6.756718879272925]
RareSpot is a robust detection framework integrating multi-scale consistency learning and context-aware augmentation.<n>Our method achieves state-of-the-art performance, improving detection accuracy by over 35% compared to baseline methods.
arXiv Detail & Related papers (2025-06-23T20:03:43Z)
DEAL-YOLO: Drone-based Efficient Animal Localization using YOLO [0.0]
This work introduces a novel approach that improves small object detection in Unmanned Aerial Vehicle (UAV) images.<n>Deal-YOLO employs multi-objective loss functions like Wise IoU (WIoU) and Normalized Wasserstein Distance (NWD), which prioritize pixels near the centre of the bounding box.<n>The model is optimized through efficient feature extraction with Linear Deformable (LD) convolutions, enhancing accuracy while maintaining computational efficiency.
arXiv Detail & Related papers (2025-03-06T18:46:10Z)
PAD-F: Prior-Aware Debiasing Framework for Long-Tailed X-ray Prohibited Item Detection [56.25222232778367]
The distribution of object classes in real-world prohibited item detection scenarios often exhibits a distinct long-tailed distribution.<n>We introduce the Prior-Aware Debiasing Framework (PAD-F), a novel approach that employs a two-pronged strategy.<n>PAD-F significantly boosts the performance of multiple popular detectors.
arXiv Detail & Related papers (2024-11-27T06:13:56Z)
Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark [101.23684938489413]
Anomaly detection (AD) is often focused on detecting anomalies for industrial quality inspection and medical lesion examination. This work first constructs a large-scale and general-purpose COCO-AD dataset by extending COCO to the AD field. Inspired by the metrics in the segmentation field, we propose several more practical threshold-dependent AD-specific metrics.
arXiv Detail & Related papers (2024-04-16T17:38:26Z)
Bootstrapping Rare Object Detection in High-Resolution Satellite Imagery [2.242884292006914]
This paper addresses the problem of bootstrapping such a rare object detection task. We propose novel offline and online cluster-based approaches for sampling patches. We apply our methods for identifying bomas, or small enclosures for herd animals, in the Serengeti Mara region of Kenya and Tanzania.
arXiv Detail & Related papers (2024-03-05T07:44:13Z)
Augment and Criticize: Exploring Informative Samples for Semi-Supervised Monocular 3D Object Detection [64.65563422852568]
We improve the challenging monocular 3D object detection problem with a general semi-supervised framework. We introduce a novel, simple, yet effective Augment and Criticize' framework that explores abundant informative samples from unlabeled data. The two new detectors, dubbed 3DSeMo_DLE and 3DSeMo_FLEX, achieve state-of-the-art results with remarkable improvements for over 3.5% AP_3D/BEV (Easy) on KITTI.
arXiv Detail & Related papers (2023-03-20T16:28:15Z)
ReDFeat: Recoupling Detection and Description for Multimodal Feature Learning [51.07496081296863]
We recouple independent constraints of detection and description of multimodal feature learning with a mutual weighting strategy. We propose a detector that possesses a large receptive field and is equipped with learnable non-maximum suppression layers. We build a benchmark that contains cross visible, infrared, near-infrared and synthetic aperture radar image pairs for evaluating the performance of features in feature matching and image registration tasks.
arXiv Detail & Related papers (2022-05-16T04:24:22Z)
Potato Crop Stress Identification in Aerial Images using Deep Learning-based Object Detection [60.83360138070649]
The paper presents an approach for analyzing aerial images of a potato crop using deep neural networks. The main objective is to demonstrate automated spatial recognition of a healthy versus stressed crop at a plant level. Experimental validation demonstrated the ability for distinguishing healthy and stressed plants in field images, achieving an average Dice coefficient of 0.74.
arXiv Detail & Related papers (2021-06-14T21:57:40Z)
Pretrained equivariant features improve unsupervised landmark discovery [69.02115180674885]
We formulate a two-step unsupervised approach that overcomes this challenge by first learning powerful pixel-based features. Our method produces state-of-the-art results in several challenging landmark detection datasets.
arXiv Detail & Related papers (2021-04-07T05:42:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.