论文标题
平衡的对称交叉熵，用于大规模不平衡和嘈杂数据
Balanced Symmetric Cross Entropy for Large Scale Imbalanced and Noisy Data
论文作者
论文摘要
深层卷积神经网络吸引了大规模视觉分类任务的许多注意事项，与传统的视觉分析方法相比，性能得到了显着改善。在本文中，我们探讨了许多深层卷积神经网络体系结构，以实现大规模的产品识别任务，这是班级失去平衡和嘈杂的标记数据，使其更加挑战。广泛的实验表明，PNASNET在各种卷积体系结构中取得了最佳性能。连同整体技术和嘈杂标记数据的负面学习损失一起，我们进一步提高了在线测试数据上的模型性能。最后，我们提出的方法在在线测试数据上达到了0.1515的平均TOP-1错误。
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.
