Boosting Weakly Supervised Object Detection using Fusion and Priors from Hallucinated Depth
Boosting Weakly Supervised Object Detection using Fusion and Priors from Hallucinated Depth
复制标题
DOI：
10.1109/wacv57701.2024.00079
复制
发表时间：
2023-03
期刊：
影响因子：
--
通讯作者：
Cagri Gungor;Adriana Kovashka
中科院分区：
文献类型：
--
作者：
Cagri Gungor;Adriana Kovashka
尽管最近关注各种任务的深度，但它仍然是弱监督对象检测（WSOD）的未开发模式。我们提出了一种放大器的方法，通过集成深度信息来增强WSOD的性能。我们的方法可以应用于不同的WSOD方法的基础上多实例学习，而不需要额外的注释或诱导大的计算成本。我们提出的方法采用单目深度估计，以获得幻觉的深度信息，然后将其纳入暹罗WSOD网络使用对比损失和融合。通过分析语言上下文和深度之间的关系，我们计算深度先验来识别可能包含感兴趣对象的边界框建议。然后，这些深度先验被用来更新伪地面实况框的列表，或者调整每个框预测的置信度。我们评估我们提出的方法在三个数据集（COCO，PASCAL VOC和概念字幕）上实现它的两个国家的最先进的WSOD方法，我们表现出显着的性能增强。
Despite recent attention to 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 different WSOD methods based on multiple-instance learning, without necessitating additional annotations or inducing large computational cost. Our proposed method employs monocular depth estimation 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. We evaluate our proposed method on three datasets (COCO, PASCAL VOC, and Conceptual Captions) by implementing it on top of two state-of-the-art WSOD methods, and we demonstrate a substantial enhancement in performance.