Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both funding and expertise. By selecting unlabeled examples that are promising in terms of model improvement and only asking for respective labels, active learning can increase the efficiency of the labeling process in terms of time and cost. In this work, we describe combinations of an incremental learning scheme and methods of active learning. These allow for continuous exploration of newly observed unlabeled data. We describe selection criteria based on model uncertainty as well as expected model output change (EMOC). An object detection task is evaluated in a continuous exploration context on the PASCAL VOC dataset. We also validate a weakly supervised system based on active and incremental learning in a real-world biodiversity application where images from camera traps are analyzed. Labeling only 32 images by accepting or rejecting proposals generated by our method yields an increase in accuracy from 25.4% to 42.6%.

中文翻译：

---

弱监督下的主动增量学习

大量标记的训练数据是深度模型过去取得巨大成功的主要贡献者之一。由于资金和专业知识的要求，基准以外任务的标签获取可能会带来挑战。通过选择在模型改进方面有前景的未标记示例并仅要求相应的标签，主动学习可以在时间和成本方面提高标记过程的效率。在这项工作中，我们描述了增量学习方案和主动学习方法的组合。这些允许持续探索新观察到的未标记数据。我们描述了基于模型不确定性以及预期模型输出变化 (EMOC) 的选择标准。在 PASCAL VOC 数据集上的连续探索上下文中评估对象检测任务。我们还在现实世界的生物多样性应用中验证了基于主动和增量学习的弱监督系统，其中分析了来自相机陷阱的图像。通过接受或拒绝由我们的方法生成的建议，仅标记 32 张图像可将准确率从 25.4% 提高到 42.6%。