Attention guidance is an approach to addressing dataset bias in deep learning, where the model relies on incorrect features to make decisions. Focusing on image classification tasks, we propose an efficient human-in-the-loop system to interactively direct the attention of classifiers to the regions specified by users, thereby reducing the influence of co-occurrence bias and improving the transferability and interpretability of a DNN. Previous approaches for attention guidance require the preparation of pixel-level annotations and are not designed as interactive systems. We present a new interactive method to allow users to annotate images with simple clicks, and study a novel active learning strategy to significantly reduce the number of annotations. We conducted both a numerical evaluation and a user study to evaluate the proposed system on multiple datasets. Compared to the existing non-active-learning approach which usually relies on huge amounts of polygon-based segmentation masks to fine-tune or train the DNNs, our system can save lots of labor and money and obtain a fine-tuned network that works better even when the dataset is biased. The experiment results indicate that the proposed system is efficient, reasonable, and reliable.

翻译：注意力引导是解决深度学习数据集偏差问题的一种方法，该问题指模型依赖错误特征进行决策。针对图像分类任务，我们提出了一种高效的人机协同系统，通过交互方式将分类器的注意力引导至用户指定区域，从而减少共现偏差的影响，提升深度神经网络的可迁移性与可解释性。现有注意力引导方法需要准备像素级标注，且未设计为交互系统。我们提出了一种新型交互方法，允许用户通过简单点击完成图像标注，并研究了一种新颖的主动学习策略以显著减少标注数量。我们在多个数据集上开展了数值评估与用户研究。与通常依赖大量多边形分割掩码来微调或训练深度神经网络的传统非主动学习方法相比，本系统可大幅节省人力与成本，即便在存在偏差的数据集上也能获得性能更优的微调网络。实验结果表明，该方案高效、合理且可靠。