TRA CỨU
thông tin biểu ghi
  • Bài trích
  • Ký hiệu PL/XG: 428.84
    Nhan đề: An effective deep learning model for recognition of animals and plants /
DDC 428.84
Tác giả CN Trinh, Thi Anh Loan
Nhan đề An effective deep learning model for recognition of animals and plants / Trinh Thi Anh Loan, Pham The Anh, Le Viet Nam..[and others]
Tóm tắt This paper presents a deep learning model to address the problem of reanixm. “Lilplants. The context of this work is to make an effort in protection of rare species that . ‘rxrinusly faced to the risk of extinction in Vietnam such as Panthera psu'é'b. Defiaergia, Macaca mulatta. The proposed approach exploits the advanced ability of Comelutional neural networks and Inception residual structures to design a model for classification task. We also apply the transfer-learning technique to fine—tune the my state-of-the-art methods, MobileNetV2 and InceptionV3, specific to our own dataset. Experimental results demonstrate the superiority of our object predictor (97.6% accuracy) in comparisjn with other methods. In addition, the proposed model works very efficiently with the inference speed of around 113 FPS on a CPU machine, enabling it for deployment on mobile environment.
Từ khóa tự do Classification losses
Từ khóa tự do Classification losses
Từ khóa tự do Deep learning models
Tác giả(bs) CN Le, Viet Nam
Tác giả(bs) CN Pham, The Anh
Nguồn trích Tạp chí Tin học và Điều khiển học = Journal of Computer Science And Cybernetics 2022tr. 32-62 Số: 01
000 00000nab#a2200000ui#4500
00152445
0029
0046FB251AE-AE6B-49B6-B5FF-97BF4BD95714
005202409261128
008081223s VN| vie
0091 0
039|y20240926113241|ztainguyendientu
040 |aACTVN
041 |avie
044 |avm
082 |a428.84
10010|aTrinh, Thi Anh Loan
245 |aAn effective deep learning model for recognition of animals and plants / |cTrinh Thi Anh Loan, Pham The Anh, Le Viet Nam..[and others]
520 |aThis paper presents a deep learning model to address the problem of reanixm. “Lilplants. The context of this work is to make an effort in protection of rare species that . ‘rxrinusly faced to the risk of extinction in Vietnam such as Panthera psu'é'b. Defiaergia, Macaca mulatta. The proposed approach exploits the advanced ability of Comelutional neural networks and Inception residual structures to design a model for classification task. We also apply the transfer-learning technique to fine—tune the my state-of-the-art methods, MobileNetV2 and InceptionV3, specific to our own dataset. Experimental results demonstrate the superiority of our object predictor (97.6% accuracy) in comparisjn with other methods. In addition, the proposed model works very efficiently with the inference speed of around 113 FPS on a CPU machine, enabling it for deployment on mobile environment.
653 |aClassification losses
653 |aClassification losses
653 |aDeep learning models
700 |aLe, Viet Nam
700 |aPham, The Anh
7730 |tTạp chí Tin học và Điều khiển học = Journal of Computer Science And Cybernetics |d2022|gtr. 32-62|x1813-9663|i01
890|a0|b0|c1|d0
Không tìm thấy biểu ghi nào