Abstract
Despite recent attention and exploration of depth for various tasks, it is still an unexplored modality for weakly-supervised object detection (WSOD). We propose an amplifier method for enhancing the performance of WSOD by integrating depth information. Our approach can be applied to any WSOD method based on multiple-instance learning, without necessitating additional annotations or inducing large computational expenses. Our proposed method employs a monocular depth estimation technique to obtain hallucinated depth information, which is then incorporated into a Siamese WSOD network using contrastive loss and fusion. By analyzing the relationship between language context and depth, we calculate depth priors to identify the bounding box proposals that may contain an object of interest. These depth priors are then utilized to update the list of pseudo ground-truth boxes, or adjust the confidence of per-box predictions. Our proposed method is evaluated on six datasets (COCO, PASCAL VOC, Conceptual Captions, Clipart1k, Watercolor2k, and Comic2k) by implementing it on top of two state-of-the-art WSOD methods, and we demonstrate a substantial enhancement in performance.
Abstract (translated)
尽管最近对深度在各种任务上的关注和研究增多,但对于弱监督对象检测(WSOD)的方法,仍然未进行充分的探索。我们提出了一种集成深度信息来提高WSOD性能的方法。这种方法可以适用于基于多实例学习的任何WSOD方法,而不需要额外的标注或高昂的计算成本。我们的方法使用单眼深度估计技术来获取幻觉深度信息,然后将其集成到使用对比损失和融合的Siamese WSOD网络中。通过分析语言上下文和深度之间的关系,我们计算深度先验,以确定可能包含感兴趣对象的 bounding box提议。这些深度先验则用于更新伪真实标签盒子列表,或调整每个盒子的预测 confidence。我们的方法在六个数据集(COCO、PASCAL VOC、概念标题、Clipart1k、Watercolor2k和漫画2k)上进行评估,将其置于两个最先进的WSOD方法之上,并证明了性能的重大增强。
URL
https://arxiv.org/abs/2303.10937
