# Weakly supervised framework for wildlife detection and counting in challenging Arctic environments: a case study on caribou (Rangifer tarandus)

arXiv: https://arxiv.org/abs/2601.18891 · HTML: https://mlsanity.com/paper/2601.18891/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 79 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Builds on (most cited first, 22 of 22)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data](https://mlsanity.com/paper/2103.16607/) (2021)
- [Self-supervised Learning in Remote Sensing: A Review](https://mlsanity.com/paper/2206.13188/) (2022)
- [CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding](https://mlsanity.com/paper/2304.09670/) (2023)
- [Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery](https://mlsanity.com/paper/1807.02700/) (2018)
- [Revisiting pre-trained remote sensing model benchmarks: resizing and normalization matters](https://mlsanity.com/paper/2305.13456/) (2023)
- [Multispecies Animal Re-ID Using a Large Community-Curated Dataset](https://mlsanity.com/paper/2412.05602/) (2024)
- [Generic Knowledge Boosted Pre-training For Remote Sensing Images](https://mlsanity.com/paper/2401.04614/) (2024)
- [Automated wildlife image classification: An active learning tool for ecological applications](https://mlsanity.com/paper/2303.15823/) (2023)
- [Dynamic Curriculum Learning for Great Ape Detection in the Wild](https://mlsanity.com/paper/2205.00275/) (2022)
- [Weaker Than You Think: A Critical Look at Weakly Supervised Learning](https://mlsanity.com/paper/2305.17442/) (2023)
- [POLO -- Point-based, multi-class animal detection](https://mlsanity.com/paper/2410.11741/) (2024)
- [Do we still need ImageNet pre-training in remote sensing scene classification?](https://mlsanity.com/paper/2111.03690/) (2021)
- [Detection of Endangered Deer Species Using UAV Imagery: A Comparative Study Between Efficient Deep Learning Approaches](https://mlsanity.com/paper/2506.00154/) (2025)
- [Self-Supervised Pretraining on Satellite Imagery: a Case Study on Label-Efficient Vehicle Detection](https://mlsanity.com/paper/2210.11815/) (2022)
- [Object counting from aerial remote sensing images: application to wildlife and marine mammals](https://mlsanity.com/paper/2306.10439/) (2023)
- [DeepAndes: A Self-Supervised Vision Foundation Model for Multi-Spectral Remote Sensing Imagery of the Andes](https://mlsanity.com/paper/2504.20303/) (2025)
- [Efficient Endangered Deer Species Monitoring with UAV Aerial Imagery and Deep Learning](https://mlsanity.com/paper/2506.00164/) (2025)
- [Weakly Supervised Faster-RCNN+FPN to classify animals in camera trap images](https://mlsanity.com/paper/2208.14060/) (2022)
- [PARDINUS: Weakly supervised discarding of photo-trapping empty images based on autoencoders](https://mlsanity.com/paper/2312.14812/) (2023)

## Built on by (most cited first, 1 of 1)

- [Overhead Wildlife Locator (OWL): Benchmarking Weakly Supervised Learning for Aerial Wildlife Surveys](https://mlsanity.com/paper/2606.13911/) (2026)

## Abstract (arXiv)

Caribou across the Arctic has declined in recent decades, motivating scalable and accurate monitoring approaches to guide evidence-based conservation actions and policy decisions. Manual interpretation from this imagery is labor-intensive and error-prone, underscoring the need for automatic and reliable detection across varying scenes. Yet, such automatic detection is challenging due to severe background heterogeneity, dominant empty terrain (class imbalance), small or occluded targets, and wide variation in density and scale. To make the detection model (HerdNet) more robust to these challenges, a weakly supervised patch-level pretraining based on a detection network's architecture is proposed. The detection dataset includes five caribou herds distributed across Alaska. By learning from empty vs. non-empty labels in this dataset, the approach produces early weakly supervised knowledge for enhanced detection compared to HerdNet, which is initialized from generic weights. Accordingly, the patch-based pretrain network attained high accuracy on multi-herd imagery (2017) and on an independent year's (2019) test sets (F1: 93.7%/92.6%, respectively), enabling reliable mapping of regions containing animals to facilitate manual counting on large aerial imagery. Transferred to detection, initialization from weakly supervised pretraining yielded consistent gains over ImageNet weights on both positive patches (F1: 92.6%/93.5% vs. 89.3%/88.6%), and full-image counting (F1: 95.5%/93.3% vs. 91.5%/90.4%). Remaining limitations are false positives from animal-like background clutter and false negatives related to low animal density occlusions. Overall, pretraining on coarse labels prior to detection makes it possible to rely on weakly-supervised pretrained weights even when labeled data are limited, achieving results comparable to generic-weight initialization.