Abstract
Weakly supervised object detection (WSOD) has attracted significant attention in recent years, as it does not require box-level annotations. State-of-the-art methods generally adopt a multi-module network, which employs WSDDN as the multiple instance detection network module and multiple instance refinement modules to refine performance. However, these approaches suffer from three key limitations. First, existing methods tend to generate pseudo GT boxes that either focus only on discriminative parts, failing to capture the whole object, or cover the entire object but fail to distinguish between adjacent intra-class instances. Second, the foundational WSDDN architecture lacks a crucial background class representation for each proposal and exhibits a large semantic gap between its branches. Third, prior methods discard ignored proposals during optimization, leading to slow convergence. To address these challenges, we first design a heatmap-guided proposal selector (HGPS) algorithm, which utilizes dual thresholds on heatmaps to pre-select proposals, enabling pseudo GT boxes to both capture the full object extent and distinguish between adjacent intra-class instances. We then present a weakly supervised basic detection network (WSBDN), which augments each proposal with a background class representation and uses heatmaps for pre-supervision to bridge the semantic gap between matrices. At last, we introduce a negative certainty supervision loss on ignored proposals to accelerate convergence. Extensive experiments on the challenging PASCAL VOC 2007 and 2012 datasets demonstrate the effectiveness of our framework. We achieve mAP/mCorLoc scores of 58.5%/81.8% on VOC 2007 and 55.6%/80.5% on VOC 2012, performing favorably against the state-of-the-art WSOD methods. Our code is publicly available at this https URL.
Abstract (translated)
近年来，弱监督目标检测（WSOD）因其不需要框级别标注而吸引了大量关注。目前最先进的方法通常采用多模块网络结构，其中包括使用WSDDN作为多次实例检测网络模块，并且有多个实例细化模块来提升性能表现。然而，这些方法面临三个关键局限性：首先，现有的方法倾向于生成伪GT（Ground Truth）框，要么只聚焦于具有区分性的部分而未能捕捉整个对象，要么覆盖了整个对象但无法在相邻的同类实例之间进行区分；其次，基础的WSDDN架构缺乏每个提议的关键背景类表示，并且其分支之间的语义差距较大；最后，先前的方法在优化过程中舍弃被忽略的提议，导致收敛速度缓慢。 为了解决这些挑战，我们首先设计了一种热图引导提案选择器（HGPS）算法，利用热图上的双阈值来预选提案，使伪GT框能够同时捕捉整个对象范围并区分相邻同类实例。接下来，我们提出了一种弱监督基本检测网络（WSBDN），它在每个提议中添加了背景类表示，并使用热图进行预先监督以缩小矩阵之间的语义差距。最后，我们在被忽略的提案上引入了一个负确定性监督损失，以加速收敛过程。 在具有挑战性的PASCAL VOC 2007和2012数据集上的广泛实验展示了我们框架的有效性。我们的方法在VOC 2007上获得了58.5%/81.8%的mAP/mCorLoc得分，在VOC 2012上则为55.6%/80.5%，相对于现有的最先进的WSOD方法表现出了明显的优越性。我们的代码可公开获取，地址见文中的链接。 此翻译旨在传达原文的技术内容和研究成果，相关技术细节与专业术语保持不变。
URL
https://arxiv.org/abs/2509.08289
