Multi-Source Weak Supervision Fusion for Disaster Scene Recognition in Videos
Multi-Source Weak Supervision Fusion for Disaster Scene Recognition in Videos
复制标题
DOI：
10.1109/mipr54900.2022.00058
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
Maria Presa-Reyes;Yudong Tao;Rui Ma;Shu‐Ching Chen;Mei-Ling Shyu
中科院分区：
文献类型：
--
作者：
Maria Presa-Reyes;Yudong Tao;Rui Ma;Shu‐Ching Chen;Mei-Ling Shyu
图像或视频记录有助于紧急救援人员在灾难事件发生后快速检查损坏情况。需要新的技术来帮助响应者在正确的时间组织和找到重要的信息。然而，由于缺乏训练数据，大多数现有方法不符合公共安全标准。我们提出了一种多源弱监督融合技术，用于在带有噪声标签的高度不平衡数据集上进行训练。使用Confident Learning技术，我们在提高类标签质量的同时降低了噪声影响。我们结合了联合收割机的预测能力，从大规模的视觉数据集上使用差分进化训练的模型。这项研究展示了一种全自动的方法，具有很大的潜力，可以减少所需的时间和资源，同时提供出色的结果。在TRECVID 2021灾难场景描述和索引（DSDI）挑战赛中，我们的技术在所有提交的运行中获得了最高分，与所使用的训练数据无关。
Images or video recordings assist emergency responders in quickly inspecting the damage after a disaster event. New techniques are needed to help responders organize and find important information at the right time. However, most existing methods do not meet public safety standards due to a lack of training data. We propose a multi-source weak supervision fusion technique to train on a highly imbalanced dataset annotated with noisy labels. Using a Confident Learning technique, we reduce the noise effect while boosting the class labels' quality. We combine the predictive power from models trained on large-scale visual datasets using Differential Evolution. This research demonstrates a fully-automatic approach with great potential to reduce the required time and resources while delivering exceptional results. In the TRECVID2021 Disaster Scene Description and Indexing (DSDI) Challenge, our technique achieved the top score among all the submitted runs, independent of the training data utilized.