Image-level weakly supervised semantic segmentation (WSSS) relies on class activation maps (CAMs) for pseudo labels generation. As CAMs only highlight the most discriminative regions of objects, the generated pseudo labels are usually unsatisfactory to serve directly as supervision. To solve this, most existing approaches follow a multi-training pipeline to refine CAMs for better pseudo-labels, which includes: 1) re-training the classification model to generate CAMs; 2) post-processing CAMs to obtain pseudo labels; and 3) training a semantic segmentation model with the obtained pseudo labels. However, this multi-training pipeline requires complicated adjustment and additional time. To address this, we propose a class-conditional inference strategy and an activation aware mask refinement loss function to generate better pseudo labels without re-training the classifier. The class conditional inference-time approach is presented to separately and iteratively reveal the classification network's hidden object activation to generate more complete response maps. Further, our activation aware mask refinement loss function introduces a novel way to exploit saliency maps during segmentation training and refine the foreground object masks without suppressing background objects. Our method achieves superior WSSS results without requiring re-training of the classifier.
翻译:为解决这一问题,大多数现有办法都采用多培训管道,改进计算机制造商分类,改进假标签,包括:(1) 重新培训分类模型,以生成计算机制造商;(2) 后处理计算机制造商,以获取假标签;和(3) 以获得的假标签来培训一个语义分类分解模型。然而,由于这一多培训管道需要复杂的调整和额外时间。要解决这个问题,我们提议一个类条件推断策略和启动有意识的遮罩改进损耗益功能,以生成更好的假标签,而不对分类器进行再培训。提出等级有条件的授精时间方法,以便分别和迭代地披露分类网络隐藏的物体,以生成更完整的响应地图。此外,我们的感知面罩改进功能引入了一种新颖的方法,在分解培训和改进前方物体时利用突出的地图,而无需压缩背景物体。