arXiv Computer Vision

Degradation-based augmented training for robust individual animal re-identification

arXiv AI
Sep 10

What Does Animal Re-Identification Learn? Linear Biological Concepts and Their Origins in Visual Representations

The study investigates whether Vision Transformer (ViT)-based animal re-identification models learn biologically meaningful concepts. Using a DINOv3 backbone fine‑tuned on Western lowland gorilla images, the authors find that sex and age emerge as linear directions in the model’s representations, generalizing to unseen individuals with high AUROC scores. They demonstrate that the sex direction is causally used by the model, that fine‑tuning relocates these concepts within the network, and that the representations reflect a graded biological axis encoded redundantly across the population.

By Robert Nolting, Alexandra Schild, Moritz Weckbecker, Maximilian Schall, Gerard de Melo
arXiv Computer Vision
3d ago

GorillaWatch: An Automated System for In-the-Wild Gorilla Re-Identification and Population Monitoring

arXiv:2512.07776v2 Announce Type: replace Abstract: Monitoring critically endangered western lowland gorillas is currently hampered by the immense manual effort required to re-identify individuals fr...

By Maximilian Schall, Felix Leonard Kn\"ofel, Noah Elias K\"onig, Jan Jonas Kubeler, Maximilian von Klinski, Joan Wilhelm Linnemann, Xiaoshi Liu, Iven Jelle Schlegelmilch, Ole Woyciniuk, Alexandra Schild, Dante Wasmuht, Magdalena Bermejo Espinet, German Illera Basas, Gerard de Melo
arXiv AI
Aug 20

Visual-Prompt Guided Wildlife Instance-Level Recognition

The paper introduces a one-stage end-to-end model for wildlife instance-level recognition that integrates detection and re-identification within a single latent space. It leverages DINOv2 for spatial geometry and MegaDescriptor for re-identification, while enhancing latent queries with prompt re-identification features. Preliminary results show a competitive mean average precision of 30.584% compared to the state-of-the-art two-stage approach of 44.89%, with qualitative evidence of effective bounding and identification of animal identities.

By Mufhumudzi Muthivhi, Jiahao Huo, Terence van Zyl, Fredrik Gustafsson
arXiv AI
Jun 2

CAFOSat: A Strongly Annotated Dataset for Infrastructure-Aware CAFO Mapping Using High-Resolution Imagery

arXiv:2606. 00548v1 Announce Type: cross Abstract: Concentrated Animal Feeding Operations (CAFOs) play an important role in agricultural production but are also associated with environmental, public health, and disease surveillance concerns.

By Oishee Bintey Hoque, Nibir Chandra Mandal, Mandy L Wilson, Samarth Swarup, Madhav Marathe, Abhijin Adiga
arXiv AI
Jun 16

Advanced Machine Learning and Deep Learning Techniques for Enhanced Cattle Identification and Detection: A Comprehensive Review

arXiv:2606. 15655v1 Announce Type: new Abstract: The need for effective cattle identification technology is now more acutely felt than ever in maintaining biosecurity, food safety, and supply chain efficacy in livestock management.

By Fayazunnesa Chowdhury, Syed Md. Galib, Md Nasim Adnan, Md. Moradul Siddique, Md Robiul Karim, K M Tanvir Anjum
arXiv AI
Aug 3

Leveraging Image Generators to Address Data Scarcity: The Gen4Regen Dataset for Forest Regeneration Mapping

arXiv:2605. 05627v2 Announce Type: replace-cross Abstract: Sustainable forest management relies on precise species composition mapping, yet traditional ground surveys are labour-intensive and geographically constrained.

By Gabriel Jeanson, David-Alexandre Duclos, William Larriv\'ee-Hardy, No\'e Cochet, Mat\v{e}j Boxan, Anthony Desch\^enes, Fran\c{c}ois Pomerleau, Philippe Gigu\`ere
arXiv Computer Vision
Aug 28

Learning Woody Clearing With Loss Alignment for Zero-Shot Regrowth and Woody Segmentation

The paper presents a deep learning approach for detecting woody clearing using bitemporal Sentinel‑2 imagery from New South Wales, Australia. By introducing a loss‑scaling coefficient, the authors align the model’s objective with end‑user metrics, boosting precision and recall. They further demonstrate zero‑shot transfer to woody regrowth and segmentation tasks, achieving significant error reductions and high F1 scores through image augmentation and generation techniques.

By Kal Backman, Jared Wood, Adam Roff