Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
153 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A Parallel Attention Network for Cattle Face Recognition (2403.19980v1)

Published 29 Mar 2024 in cs.CV

Abstract: Cattle face recognition holds paramount significance in domains such as animal husbandry and behavioral research. Despite significant progress in confined environments, applying these accomplishments in wild settings remains challenging. Thus, we create the first large-scale cattle face recognition dataset, ICRWE, for wild environments. It encompasses 483 cattle and 9,816 high-resolution image samples. Each sample undergoes annotation for face features, light conditions, and face orientation. Furthermore, we introduce a novel parallel attention network, PANet. Comprising several cascaded Transformer modules, each module incorporates two parallel Position Attention Modules (PAM) and Feature Mapping Modules (FMM). PAM focuses on local and global features at each image position through parallel channel attention, and FMM captures intricate feature patterns through non-linear mappings. Experimental results indicate that PANet achieves a recognition accuracy of 88.03% on the ICRWE dataset, establishing itself as the current state-of-the-art approach. The source code is available in the supplementary materials.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (31)
  1. “An evaluation of retinal imaging technology for 4-h beef and sheep identification,” JOE, vol. 44, pp. 9, 2006.
  2. “Research on the application of iris recognition in meat-food supply chain management,” CSSJ, vol. 19, pp. 6, 2009.
  3. “Image-based individual cow recognition using body patterns,” IJACSA, vol. 11, pp. 92–98, 2020.
  4. “A computer vision pipeline that uses thermal and rgb images for the recognition of holstein cattle,” in CAIP, 2019, pp. 108–119.
  5. “Cattle face recognition method based on parameter transfer and deep learning,” in JPCS, 2020, vol. 1453, p. 012054.
  6. “Deep learning framework for recognition of cattle using muzzle point image pattern,” Measurement, vol. 116, pp. 1–17, 2018.
  7. “Cattle face recognition using sparse representation classifier,” ICIC-ELB, vol. 3, pp. 1499–1505, 2012.
  8. “Bull face recognition algorithm based on vision transformer model,” Journal of Hangzhou Dianzi University, vol. 42, pp. 40–46, 2022.
  9. “Leformer: A hybrid cnn-transformer architecture for accurate lake extraction from remote sensing imagery,” arXiv preprint arXiv:2308.04397, 2023.
  10. “Diffcr: A fast conditional diffusion framework for cloud removal from optical satellite images,” arXiv preprint arXiv:2308.04417, 2023.
  11. “Pmaa: A progressive multi-scale attention autoencoder model for high-performance cloud removal from multi-temporal satellite imagery,” in ECAI, 2023, pp. 3165–3172.
  12. “Survey of single image super-resolution reconstruction,” IET Image Processing, vol. 14, pp. 2273–2290, 2020.
  13. “An efficient encoder-decoder architecture with top-down attention for speech separation,” in ICLR, 2022, pp. 1–16.
  14. “Inferring mechanisms of auditory attentional modulation with deep neural networks,” Neural Computation, vol. 34, pp. 2273–2293, 2022.
  15. “Squeeze-and-excitation networks,” in CVPR, 2018, pp. 7132–7141.
  16. “Cbam: Convolutional block attention module,” in ECCV, 2018, pp. 3–19.
  17. “Eca-net: Efficient channel attention for deep convolutional neural networks,” in CVPR, 2020, pp. 11534–11542.
  18. “An image is worth 16x16 words: Transformers for image recognition at scale,” in ICLR, 2021, pp. 1–21.
  19. “Swin transformer: Hierarchical vision transformer using shifted windows,” in ICCV, 2021, pp. 10012–10022.
  20. “A convnet for the 2020s,” in CVPR, 2022, pp. 11976–11986.
  21. “Individual identification of dairy cows based on convolutional neural networks,” MTA, vol. 79, pp. 14711–14724, 2020.
  22. “Design of cow face recognition system for insurance businesses based on three-dimensional loss algorithm,” Journal of Optoelectronics.Laser, vol. 33, pp. 832–839, 2022.
  23. “Research and implementation of a cattle face recognition system model combining cnn with svm and resnet,” Journal of Chongqing University of Technology, vol. 36, pp. 156–161, 2022.
  24. “Facenet: A unified embedding for face recognition and clustering,” in CVPR, 2015, pp. 815–823.
  25. “Deep residual learning for image recognition,” in CVPR, 2016, pp. 770–778.
  26. “Mobilenetv2: Inverted residuals and linear bottlenecks,” in CVPR, 2018, pp. 4510–4520.
  27. “Shufflenet v2: Practical guidelines for efficient cnn architecture design,” in ECCV, 2018, pp. 116–131.
  28. “Res2net: A new multi-scale backbone architecture,” PAMI, vol. 43, pp. 652–662, 2019.
  29. “Efficientnet: Rethinking model scaling for convolutional neural networks,” in ICML, 2019, pp. 6105–6114.
  30. “Deep high-resolution representation learning for human pose estimation,” in CVPR, 2019, pp. 5693–5703.
  31. “Simple baselines for image restoration,” in ECCV, 2022, pp. 17–33.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets