MULTI-SCALE CROSS-FUSION FINE-GRAINED NETWORK FOR IDENTIFYING INVASIVE PLANTS

Hang Sun, Yuting Zang, Lu Wang, Shun Ren, Xidong Wang, and Xiaolin Chen

References

  1. [1] G. Van Horn, O. Mac Aodha, Y. Song, Y. Cui, C. Sun,A.Shepard, H. Adam, P. Perona, and S. Belongie, Theinaturalist species classification and detection dataset, Proc. ofthe IEEE Conf. on Computer Vision and Pattern Recognition,2018, 8769–8778.
  2. [2] Y. Wu, X. Qin, Y. Pan, and C. Yuan, Convolution neuralnetwork based transfer learning for classification of flowers,Proc. 2018 IEEE 3rd International Conf. on Signal and ImageProcessing (ICSIP), Shenzhen, 2018, 562–566.
  3. [3] C. Wah, S. Branson, P. Welinder, P. Perona, and S. Be- Longie,The caltech-UCSD birds-200-2011 dataset, 2011.
  4. [4] Y. Wang, V.I. Morariu, and L.S. Davis, Learning adiscriminative filter bank within a CNN for fine-grainedrecognition, Proc. of the IEEE Conf. on Computer Vision andPattern Recognition, Salt Lake City, UT, 2018, 4148–4157.
  5. [5] Z. Yang, T. Luo, D. Wang, Z. Hu, J. Gao, and L. Wang,Learning to navigate for fine-grained classification, Proc. of theEuropean Conf. on Computer Vision (ECCV), Cham, 2018,420–435.
  6. [6] Y. Chen, Y. Bai, W.W. Zhang, and T. Mei, Destruction andconstruction learning for fine-grained image recognition, Proc.8of the IEEE/CVF Conf. on Computer Vision and PatternRecognition, Long Beach, CA, 2019, 5157–5166.
  7. [7] D.E. Rumelhart, G.E. Hinton, and R.J. Williams, Learningrepresentations by back-propagating errors, Nature, 323(6088),1986, 533–536.
  8. [8] R. Du, D. Chang, A.K. Bhunia, J. Xie, Z. Ma, Y.Z. Song, andJ. Guo, Fine-grained visual classification via progressive multi-granularity training of jigsaw patches, Proc. European Conf. onComputer Vision, Cham: Springer International Publishing,2020, 153–168.
  9. [9] J. Fu, H. Zheng, and T. Mei, Look closer to see better:Recurrent attention convolutional neural network for fine-grained image recognition, Proc. of the IEEE Conf. onComputer Vision and Pattern Recognition, Honolulu, HI, 2017,4438–4446.
  10. [10] H. Tang, J. Liu, S. Yan, R. Yan, Z. Li, and J. Tang, M3Net:Multi-view encoding, matching, and fusion for few-shot fine-grained action recognition, Proc. of the 31st ACM InternationalConf. on Multimedia, Ottawa ON, 2023, 1719–1728.
  11. [11] Z. Zha, H. Tang, Y. Sun, and J. Tang, Boosting few-shotfine-grained recognition with background suppression andforeground alignment, IEEE Transactions on Circuits andSystems for Video Technology, 33(8), 2023, 3947–3961.
  12. [12] H. Tang, C. Yuan, Z. Li, and J. Tang, Learning attention-guided pyramidal features for few-shot fine-grained recognition,Pattern Recognition, 130, 2022, 108792.
  13. [13] H. Zheng, J. Fu, T. Mei, and J. Luo, Learning multi-attentionconvolutional neural network for fine-grained image recognition,Proc. of the IEEE International Conf. on Computer Vision,Venice, 2017, 5209–5217.
  14. [14] H. Zheng, J. Fu, Z.J. Zha, and J. Luo, Looking for the devilin the details: Learning trilinear attention sampling networkfor fine-grained image recognition, Proc. of the IEEE/CVFConf. on Computer Vision and Pattern Recognition, 2019,5012–5021.
  15. [15] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones,and A. Gomez, Attention is all you need, Advances in NeuralInformation Processing Systems, 30, 2017.
  16. [16] A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X.Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold,S. Gelly, J. Uszkoreit, and N. Houlsby, An image is worth16x16 words: Transformers for image recognition at scale, 2020,arXiv:2010.11929.
  17. [17] K. Higuchi and K. Yanai, Patent image retrieval usingtransformer-based deep metric learning, World Patent Infor-mation, 74, 2023, 102217.
  18. [18] A. Baldrati, M. Bertini, T. Uricchio, and A. Bimbo, Composedimage retrieval using contrastive learning and task-orientedCLIP-based features, ACM Transactions on MultimediaComputing, Communications and Applications, 2023.
  19. [19] A. Venkataramanan, M. Laviale, and C. Pradalier, Inte-grating visual and semantic similarity using hierarchies forimage retrieval, Proc. International Conf. on ComputerVision Systems, Cham: Springer Nature Switzerland, 2023,422–431.
  20. [20] H. Sun, Z. Luo, D. Ren, and L. Zhang, Partial siamesewith multiscale Bi-codec networks for remote sensing imagehaze removal, IEEE Transactions on Geoscience and RemoteSensing, 61, 2023, 1–16. DOI: 10.1109/TGRS.2023.3321307.
  21. [21] H. Sun, B. Li, Z. Dan, W. Hu , B. Du, W. Yang, andJ. Wan, Multi-level feature interaction and efficient non-localinformation enhanced channel attention for image dehazing,Neural Networks, 163, 2023, 10–27.
  22. [22] H. Sun, Y. Zhang, P. Chen, Z. Dan, S. Sun, J. Wan, and W.Li, Scale-free heterogeneous cycleGAN for defogging from asingle image for autonomous driving in fog, Neural Computingand Applications, 35, 2023, 3737–3751.
  23. [23] F. Schroff, D. Kalenichenko, and J. Philbin, Facenet: A unifiedembedding for face recognition and clustering, Proc. of theIEEE Conf. on Computer Vision and Pattern Recognition,Boston, MA, 2015, 815–823.
  24. [24] J. Deng, J. Guo, N. Xue, and S. Zafeiriou, Arcface: Additiveangular margin loss for deep face recognition, Proc. ofthe IEEE/CVF Conf. on Computer Vision and PatternRecognition, Long Beach, CA, 2019, 4690–4699.
  25. [25] J. He, J.N. Chen, S. Liu, A. Kortylewski, C. Yang, Y.Bai, andC. Wang, Transfg: A transformer architecture for fine-grainedrecognition, Proceedings of the AAAI Conference on ArtificialIntelligence, 36(1), 2022, 852–860.
  26. [26] Y. Wen, K. Zhang, Z. Li, and Y. Qiao, A discriminative featurelearning approach for deep face recognition, Proc. ComputerVision–ECCV 2016: 14th European Conf., Amsterdam, TheNetherlands, October 11–14, 2016, Proceedings, Part VII 14.Springer International Publishing, 2016, 499–515.
  27. [27] J.C. Su and S. Maji, The semi-supervised inaturalist challengeat the FGVC8 workshop, 2021, arXiv:2106.01364.
  28. [28] T. Zhang, D. Chang, Z. Ma, and J. Guo, Progressive co-attention network for fine-grained visual classification, Proc.2021 International Conf. on Visual Communications and ImageProcessing (VCIP), IEEE, Munich, 2021, 1–5.
  29. [29] X. Yang, Y. Wang, K. Chen, Y. Xu, and Y. Tian, Fine-grainedobject classification via self-supervised pose alignment, Proc.of the IEEE/CVF Conf. on Computer Vision and PatternRecognition, 2022, 7399–7408.
  30. [30] Y. Liang, L. Zhu, X. Wang, and Y Yang, Penalizing the hardexample but not too much: A strong baseline for fine-grainedvisual classification, IEEE Transactions on Neural Networksand Learning Systems, 2022.
  31. [31] Q. Diao, Y. Jiang, B. Wen, J. Sun, and Z. Yuan, Metaformer:A unified meta framework for fine-grained recognition, 2022,arXiv:2203.02751.

Important Links:

Go Back