Balanced Symmetric Cross Entropy for Large Scale Imbalanced and Noisy Data
This work addresses product recognition for e-commerce or similar applications, but it is incremental as it combines existing methods like PNASNet and negative learning.
The paper tackled large-scale product recognition with class-imbalanced and noisy labeled data, achieving a mean top-1 error of 0.1515 on online test data by using PNASNet with ensemble techniques and negative learning loss.
Deep convolution neural network has attracted many attentions in large-scale visual classification task, and achieves significant performance improvement compared to traditional visual analysis methods. In this paper, we explore many kinds of deep convolution neural network architectures for large-scale product recognition task, which is heavily class-imbalanced and noisy labeled data, making it more challenged. Extensive experiments show that PNASNet achieves best performance among a variety of convolutional architectures. Together with ensemble technology and negative learning loss for noisy labeled data, we further improve the model performance on online test data. Finally, our proposed method achieves 0.1515 mean top-1 error on online test data.