Abstract
Scarcity of pixel-level labels is a significant challenge in practical scenarios. In specific domains like industrial smoke, acquiring such detailed annotations is particularly difficult and often requires expert knowledge. To alleviate this, weakly supervised semantic segmentation (WSSS) has emerged as a promising approach. However, due to the supervision gap and inherent bias in models trained with only image level labels, existing WSSS methods suffer from limitations such as incomplete foreground coverage, inaccurate object boundaries, and spurious correlations, especially in our domain, where emissions are always spatially coupled with chimneys. Previous solutions typically rely on additional priors or external knowledge to mitigate these issues, but they often lack scalability and fail to address the model's inherent bias toward co-occurring context. To address this, we propose a novel WSSS framework that directly targets the co-occurrence problem without relying on external supervision. Unlike prior methods that adopt a single network, we employ a teacher-student framework that combines CNNs and ViTs. We introduce a knowledge transfer loss that enforces cross-architecture consistency by aligning internal representations. Additionally, we incorporate post-processing techniques to address partial coverage and further improve pseudo mask quality.
Abstract (translated)
像素级标签的稀缺性在实际场景中是一个重大挑战。特别是在工业烟雾等特定领域，获取这些详细标注尤为困难，并且通常需要专家知识。为了解决这一问题，弱监督语义分割（WSSS）作为一种有前景的方法应运而生。然而，由于仅使用图像级别标签进行训练时模型中存在的监督差距和固有偏差，现有的WSSS方法面临着诸如前景覆盖不全、对象边界不准确以及虚假相关等问题的限制，特别是在我们的领域中，排放总是与烟囱空间上耦合。先前的解决方案通常依赖于额外先验知识或外部信息来缓解这些问题，但它们往往缺乏可扩展性且无法解决模型对共现上下文的固有偏差问题。 为了解决这个问题，我们提出了一种新的WSSS框架，该框架直接针对共现问题，并不依赖于外部监督。不同于以往采用单一网络的方法，我们使用了一个教师-学生框架结合CNN和ViT。我们引入了知识迁移损失，通过对齐内部表示来强制跨架构的一致性。此外，我们还采用了后处理技术以解决部分覆盖问题并进一步提高伪标签掩码的质量。 这种方法旨在克服现有WSSS方法的局限性，并提供一个更具可扩展性和鲁棒性的解决方案，特别适用于工业烟雾等空间共现特征明显的场景。
URL
https://arxiv.org/abs/2507.21959
