Cross-Species Transfer Learning in Agricultural AI: Evaluating ZebraPose Adaptation for Dairy Cattle Pose Estimation

• URL: http://arxiv.org/abs/2510.22618v1
• Date: Sun, 26 Oct 2025 10:31:22 GMT
• Title: Cross-Species Transfer Learning in Agricultural AI: Evaluating ZebraPose Adaptation for Dairy Cattle Pose Estimation
• Authors: Mackenzie Tapp, Sibi Chakravarthy Parivendan, Kashfia Sailunaz, Suresh Neethirajan,
• Abstract summary: This study evaluates the potential and limitations of cross-species transfer learning.<n>We adapt a vision transformer-based model trained on synthetic zebra imagery for 27-keypoint detection in dairy cows under real barn conditions.
• Score: 0.6999740786886536
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Pose estimation serves as a cornerstone of computer vision for understanding animal posture, behavior, and welfare. Yet, agricultural applications remain constrained by the scarcity of large, annotated datasets for livestock, especially dairy cattle. This study evaluates the potential and limitations of cross-species transfer learning by adapting ZebraPose - a vision transformer-based model trained on synthetic zebra imagery - for 27-keypoint detection in dairy cows under real barn conditions. Using three configurations - a custom on-farm dataset (375 images, Sussex, New Brunswick, Canada), a subset of the APT-36K benchmark dataset, and their combination, we systematically assessed model accuracy and generalization across environments. While the combined model achieved promising performance (AP = 0.86, AR = 0.87, PCK 0.5 = 0.869) on in-distribution data, substantial generalization failures occurred when applied to unseen barns and cow populations. These findings expose the synthetic-to-real domain gap as a major obstacle to agricultural AI deployment and emphasize that morphological similarity between species is insufficient for cross-domain transfer. The study provides practical insights into dataset diversity, environmental variability, and computational constraints that influence real-world deployment of livestock monitoring systems. We conclude with a call for agriculture-first AI design, prioritizing farm-level realism, cross-environment robustness, and open benchmark datasets to advance trustworthy and scalable animal-centric technologies.

Related papers

• A Computer Vision Pipeline for Individual-Level Behavior Analysis: Benchmarking on the Edinburgh Pig Dataset [0.46297934208241753]
  Animal behavior analysis plays a crucial role in understanding animal welfare, health status, and productivity in agricultural settings.<n>We present a modular pipeline that leverages open-sourced state-of-the-art computer vision techniques to automate animal behavior analysis in a group housing environment.<n>Our approach combines state-of-the-art models for zero-shot object detection, motion-aware tracking and segmentation, and advanced feature extraction using vision transformers for robust behavior recognition.
  arXiv  Detail & Related papers  (2025-09-15T15:31:12Z)
• An Explainable AI based approach for Monitoring Animal Health [0.2749898166276853]
  Monitoring cattle health and optimizing yield are key challenges faced by dairy farmers due to difficulties in tracking all animals on the farm.<n>This work aims to showcase modern data-driven farming practices based on explainable machine learning(ML) methods that explain the activity and behaviour of dairy cattle (cows)
  arXiv  Detail & Related papers  (2025-08-13T21:40:35Z)
• Multimodal AI Systems for Enhanced Laying Hen Welfare Assessment and Productivity Optimization [0.0]
  Future of poultry production depends on replacing subjective, labor-intensive welfare checks with data-driven, intelligent monitoring ecosystems.<n>Traditional welfare assessments-limited by human observation and single-sensor data-cannot fully capture the complex, multidimensional nature of laying hen welfare in modern farms.<n>This work lays the foundation for a transition from reactive, unimodal monitoring to proactive, precision-driven welfare systems that unite productivity with ethical, science based animal care.
  arXiv  Detail & Related papers  (2025-08-11T05:17:16Z)
• AI-Powered Cow Detection in Complex Farm Environments [7.956743113777889]
  Existing cow detection algorithms face challenges in real-world farming environments.<n>This study addresses these challenges using a diverse cow dataset from six environments.<n>YOLOv8-CBAM outperformed YOLOv8 by 2.3% in mAP, achieving 95.2% precision and an mAP@0.5:0.95 of 82.6%.
  arXiv  Detail & Related papers  (2025-01-03T19:54:38Z)
• Combining Observational Data and Language for Species Range Estimation [63.65684199946094]
  We propose a novel approach combining millions of citizen science species observations with textual descriptions from Wikipedia.<n>Our framework maps locations, species, and text descriptions into a common space, enabling zero-shot range estimation from textual descriptions.<n>Our approach also acts as a strong prior when combined with observational data, resulting in more accurate range estimation with less data.
  arXiv  Detail & Related papers  (2024-10-14T17:22:55Z)
• Public Computer Vision Datasets for Precision Livestock Farming: A Systematic Survey [3.3651853492305177]
  This study presents the first systematic survey of publicly available livestock CV datasets. Among 58 public datasets identified and analyzed, almost half of them are for cattle, followed by swine, poultry, and other animals. Individual animal detection and color imaging are the dominant application and imaging modality for livestock.
  arXiv  Detail & Related papers  (2024-06-15T13:22:41Z)
• One-Shot Domain Adaptive and Generalizable Semantic Segmentation with Class-Aware Cross-Domain Transformers [96.51828911883456]
  Unsupervised sim-to-real domain adaptation (UDA) for semantic segmentation aims to improve the real-world test performance of a model trained on simulated data. Traditional UDA often assumes that there are abundant unlabeled real-world data samples available during training for the adaptation. We explore the one-shot unsupervised sim-to-real domain adaptation (OSUDA) and generalization problem, where only one real-world data sample is available.
  arXiv  Detail & Related papers  (2022-12-14T15:54:15Z)
• A Novel Dataset for Evaluating and Alleviating Domain Shift for Human Detection in Agricultural Fields [59.035813796601055]
  We evaluate the impact of domain shift on human detection models trained on well known object detection datasets when deployed on data outside the distribution of the training set. We introduce the OpenDR Humans in Field dataset, collected in the context of agricultural robotics applications, using the Robotti platform.
  arXiv  Detail & Related papers  (2022-09-27T07:04:28Z)
• Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization [89.73665256847858]
  We show that out-of-distribution performance is strongly correlated with in-distribution performance for a wide range of models and distribution shifts. Specifically, we demonstrate strong correlations between in-distribution and out-of-distribution performance on variants of CIFAR-10 & ImageNet. We also investigate cases where the correlation is weaker, for instance some synthetic distribution shifts from CIFAR-10-C and the tissue classification dataset Camelyon17-WILDS.
  arXiv  Detail & Related papers  (2021-07-09T19:48:23Z)
• Zoo-Tuning: Adaptive Transfer from a Zoo of Models [82.9120546160422]
  Zoo-Tuning learns to adaptively transfer the parameters of pretrained models to the target task. We evaluate our approach on a variety of tasks, including reinforcement learning, image classification, and facial landmark detection.
  arXiv  Detail & Related papers  (2021-06-29T14:09:45Z)
• Estimating Crop Primary Productivity with Sentinel-2 and Landsat 8 using Machine Learning Methods Trained with Radiative Transfer Simulations [58.17039841385472]
  We take advantage of all parallel developments in mechanistic modeling and satellite data availability for advanced monitoring of crop productivity. Our model successfully estimates gross primary productivity across a variety of C3 crop types and environmental conditions even though it does not use any local information from the corresponding sites. This highlights its potential to map crop productivity from new satellite sensors at a global scale with the help of current Earth observation cloud computing platforms.
  arXiv  Detail & Related papers  (2020-12-07T16:23:13Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.