Weakly Supervised Object Localization (WSOL) aims to localize objects with
image-level supervision. Existing works mainly rely on Class Activation Mapping
(CAM) derived from a classification model. However, CAM-based methods usually
focus on the most discriminative parts of an object (i.e., incomplete
localization problem). In this paper, we empirically prove that this problem is
associated with the mixup of the activation values between less discriminative
foreground regions and the background. To address it, we propose Class
RE-Activation Mapping (CREAM), a novel clustering-based approach to boost the
activation values of the integral object regions. To this end, we introduce
class-specific foreground and background context embeddings as cluster
centroids. A CAM-guided momentum preservation strategy is developed to learn
the context embeddings during training. At the inference stage, the
re-activation mapping is formulated as a parameter estimation problem under
Gaussian Mixture Model, which can be solved by deriving an unsupervised
Expectation-Maximization based soft-clustering algorithm. By simply integrating
CREAM into various WSOL approaches, our method significantly improves their
performance. CREAM achieves the state-of-the-art performance on CUB, ILSVRC and
OpenImages benchmark datasets. Code will be available at
this https URL.

本文提出一种基于类聚合的新型方法 - Class RE-Activation Mapping (CREAM)，并使用 CAM-guided momentum preservation 策略学习上下文嵌入时，利用高斯混合模型推导出一种无监督的期望最大化软聚类算法，有效地解决在弱监督目标定位过程中遇到的局部不准确定位问题，并在数据集 CUB、ILSVRC 和 OpenImages 等基准数据集中实现了 state-of-the-art 的性能表现。