背景分裂：在背景海洋中寻找稀有类
Background Splitting: Finding Rare Classes in a Sea of Background
摘要：
我们专注于为少量稀有类别的图像分类训练准确深度模型的现实问题。在这些场景中，几乎所有图像都属于数据集中的背景类别（>95%的数据集是背景）。我们证明，在这种极端不平衡的情况下，标准的微调方法和最先进的方法在不平衡数据集上进行训练都不能产生准确的深度模型。我们的主要观察结果是，通过利用来自现有预训练模型的视觉知识，可以大大减少背景类别导致的极端不平衡。具体而言，在使用预训练模型的训练期间，背景类别被“分裂”成更小且更连贯的伪类别。我们通过添加辅助损失来将背景分裂并入图像分类模型中，该辅助损失学习模仿现有的预训练图像分类模型的预测。请注意，此过程是自动的，不需要额外的手动标签。辅助损失正则化共享网络干线的特征表示，要求它区分以前同质的背景实例，并减少过拟合到少数罕见的类别阳性。我们还表明，BG分裂可以与其他背景不平衡方法相结合，以进一步提高性能。我们在iNaturalist数据集的修改版本上评估了我们的方法，其中在训练过程中只有一小部分稀有类别标签可用（所有其他图像都标记为背景）。通过联合学习识别ImageNet类别和选定的iNaturalist类别，当99.98%的数据为背景时，我们的方法产生的性能比微调基线高42.3 mAP点，当98.30%的数据为背景时，比SotA基线高8.3 mAP点。
英文摘要：
We focus on the real-world problem of training accurate deep models for image classification of a small number of rare categories. In these scenarios, almost all images belong to the background category in the dataset (>95% of the dataset is background). We demonstrate that both standard fine-tuning approaches and state-of-the-art approaches for training on imbalanced datasets do not produce accurate deep models in the presence of this extreme imbalance. Our key observation is that the extreme imbalance due to the background category can be drastically reduced by leveraging visual knowledge from an existing pre-trained model. Specifically, the background category is "split" into smaller and more coherent pseudo-categories during training using a pre-trained model. We incorporate background splitting into an image classification model by adding an auxiliary loss that learns to mimic the predictions of the existing, pre-trained image classification model. Note that this process is automatic and requires no additional manual labels. The auxiliary loss regularizes the feature representation of the shared network trunk by requiring it to discriminate between previously homogeneous background instances and reduces overfitting to the small number of rare category positives. We also show that BG splitting can be combined with other background imbalance methods to further improve performance. We evaluate our method on a modified version of the iNaturalist dataset where only a small subset of rare category labels are available during training (all other images are labeled as background). By jointly learning to recognize ImageNet categories and selected iNaturalist categories, our approach yields performance that is 42.3 mAP points higher than a fine-tuning baseline when 99.98% of the data is background, and 8.3 mAP points higher than SotA baselines when 98.30% of the data is background.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
