Bag of Tricks for Retail Product Image Classification

  title={Bag of Tricks for Retail Product Image Classification},
  author={Muktabh Mayank Srivastava},
  • Muktabh Mayank Srivastava
  • Published in ICIAR 2020
  • Computer Science, Mathematics
  • Retail Product Image Classification is an important Computer Vision and Machine Learning problem for building real world systems like self-checkout stores and automated retail execution evaluation. In this work, we present various tricks to increase accuracy of Deep Learning models on different types of retail product image classification datasets. These tricks enable us to increase the accuracy of fine tuned convnets for retail product image classification by a large margin. As the most… CONTINUE READING

    Figures, Tables, and Topics from this paper.


    Publications referenced by this paper.
    ImageNet Large Scale Visual Recognition Challenge
    • 16,446
    • PDF
    Aggregated Residual Transformations for Deep Neural Networks
    • 2,680
    • Highly Influential
    • PDF
    Recognizing Products: A Per-exemplar Multi-label Image Classification Approach
    • 61
    • PDF
    How transferable are features in deep neural networks?
    • 3,917
    • Highly Influential
    • PDF
    Context-aware hybrid classification system for fine-grained retail product recognition
    • 17
    • PDF
    Exploring the Limits of Weakly Supervised Pretraining
    • 371
    • Highly Influential
    • PDF
    Fine-Grained Grocery Product Recognition by One-Shot Learning
    • 13
    Grocery product detection and recognition
    • 15
    Maximum-Entropy Fine-Grained Classification
    • 28
    • Highly Influential
    • PDF
    Domain invariant hierarchical embedding for grocery products recognition
    • 5
    • PDF