Instagram Hashtag Prediction Using Deep Neural Networks

被引：1
作者：
Beketova, Anna [1 ]
Makarov, Ilya [1 ,2 ]
机构：
[1] HSE Univ, Moscow, Russia
[2] Artificial Intelligence Res Inst, Moscow, Russia
来源：
ADVANCES IN COMPUTATIONAL INTELLIGENCE (IWANN 2021), PT II | 2021年 / 12862卷
关键词：
Deep learning; Multi-label image classification; Knowledge distillation; Multimedia;
D O I：
10.1007/978-3-030-85099-9_3
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Instagram is one of the most popular photos sharing services. For more convenient content search people use hashtags (#nature, #love, etc.) in posts with photos. The author's aim is to make hashtag prediction possible and convenient for users. The paper provides a reader with a detailed theoretical overview of Multi-Label Image Classification, Knowledge Distillation, and an overview of ResNet architecture. Next, the author proposes improvements on ResNet architecture allowing the model to boost quality and converge faster. Finally, the model type Self-Improving-Modified-Resnet (SIMR) is presented. Their main feature is the additional bottleneck block used as the tool incorporating benefits from a combination of self-training and knowledge distillation.
引用
收藏
页码：28 / 42
页数：15
相关论文
共 58 条
  • [1] [Anonymous], 2011, IJCAI Proceedings-International Joint Conference on Artificial Intelligence, DOI DOI 10.5591/978-1-57735-516-8/IJCAI11-220
  • [2] [Anonymous], 2016, Training and investigating residual nets
  • [3] [Anonymous], 2006, P 12 ACM SIGKDD INT
  • [4] Bourdev L, 2011, IEEE I CONF COMP VIS, P1543, DOI 10.1109/ICCV.2011.6126413
  • [5] Learning multi-label scene classification
    Boutell, MR
    Luo, JB
    Shen, XP
    Brown, CM
    [J]. PATTERN RECOGNITION, 2004, 37 (09) : 1757 - 1771
  • [6] Matrix Completion for Weakly-Supervised Multi-Label Image Classification
    Cabral, Ricardo
    De la Torre, Fernando
    Costeira, Joao Paulo
    Bernardino, Alexandre
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2015, 37 (01) : 121 - 135
  • [7] Multi-Label Image Recognition with Graph Convolutional Networks
    Chen, Zhao-Min
    Wei, Xiu-Shen
    Wang, Peng
    Guo, Yanwen
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 5172 - 5181
  • [8] Chua T.-S., 2009, P ACM INT C IM VID R, P1
  • [9] Dembczynski K., 2012, ARXIV PREPRINT ARXIV
  • [10] Deng J, 2009, PROC CVPR IEEE, P248, DOI 10.1109/CVPRW.2009.5206848
123456