近年来, 深度学习技术已经广泛应用到图像语义分割领域. 主要对基于深度学习的图像语义分割
的经典方法与研究现状进行分类, 梳理和总结. 根据分割特点和处理粒度的不同 …

The class activation maps are generated from the final convolutional layer of CNN. They can
highlight discriminative object regions for the class of interest. These discovered object …

Mining precise class-aware attention maps, aka, class activation maps, is essential for
weakly supervised semantic segmentation. In this paper, we present L2G, a simple online …

Despite remarkable progress, weakly supervised segmentation methods are still inferior to
their fully supervised counterparts. We obverse that the performance gap mainly comes from …

In this work, we propose Adversarial Complementary Learning (ACoL) to automatically
localize integral objects of semantic interest with weak supervision. We first mathematically …

Recent progress on saliency detection is substantial, benefiting mostly from the explosive
development of Convolutional Neural Networks (CNNs). Semantic segmentation and …

近年来, 深度学习技术已经广泛应用到图像语义分割领域. 主要对基于深度学习的图像语义分割
的经典方法与研究现状进行分类, 梳理和总结. 根据分割特点和处理粒度的不同 …

Recently, adversarial erasing for weakly-supervised object attention has been deeply
studied due to its capability in localizing integral object regions. However, such a strategy …

Object attention maps generated by image classifiers are usually used as priors for weakly-
supervised segmentation approaches. However, normal image classifiers produce attention …

We provide a comprehensive evaluation of salient object detection (SOD) models. Our
analysis identifies a serious design bias of existing SOD datasets which assumes that each …