In the wheat nutrient deficiencies classification challenge, we present the
DividE and EnseMble (DEEM) method for progressive test data predictions. We
find that (1) test images are provided in the challenge; (2) samples are
equipped with their collection dates; (3) the samples of different dates show
notable discrepancies. Based on the findings, we partition the dataset into
discrete groups by the dates and train models on each divided group. We then
adopt the pseudo-labeling approach to label the test data and incorporate those
with high confidence into the training set. In pseudo-labeling, we leverage
models ensemble with different architectures to enhance the reliability of
predictions. The pseudo-labeling and ensembled model training are iteratively
conducted until all test samples are labeled. Finally, the separated models for
each group are unified to obtain the model for the whole dataset. Our method
achieves an average of 93.6\% Top-1 test accuracy~(94.0\% on WW2020 and 93.2\%
on WR2021) and wins the 1$st$ place in the Deep Nutrient Deficiency
Challenge~\footnote{this https URL}.

我们提出了 DividE 和 EnseMble (简称 DEEM) 方法，用于逐步测试数据预测的小麦营养缺陷分类挑战，并通过将数据集分成不同日期的离散组来训练模型，并采用伪标签方法将高置信度的测试数据标记并纳入训练集，最终将各组的模型统一获得整个数据集的模型。该方法在 Deep Nutrient Deficiency Challenge 中获得了平均 93.6％的 Top-1 测试准确率（WW2020 为 94.0％，WR2021 为 93.2％）并荣获了第一名。