Abstract Despite the remarkable progress, weakly supervised segmentation approaches are still inferior to their fully supervised counterparts. We obverse the performance gap mainly comes from their limitation on learning to produce highquality dense object localization maps from image-level supervision. To mitigate such a gap, we revisit the dilated convolution [1] and reveal how it can be utilized in a novel way to effectively overcome this critical limitation of weakly supervised segmentation approaches. Specififically, we fifind that varying dilation rates can effectively enlarge the receptive fifields of convolutional kernels and more importantly transfer the surrounding discriminative information to nondiscriminative object regions, promoting the emergence of these regions in the object localization maps. Then, we design a generic classifification network equipped with convolutional blocks of different dilated rates. It can produce dense and reliable object localization maps and effectively benefifit both weakly- and semi- supervised semantic segmentation. Despite the apparent simplicity, our proposed approach obtains superior performance over state-of-thearts. In particular, it achieves 60.8% and 67.6% mIoU scores on Pascal VOC 2012 test set in weakly- (only imagelevel labels are available) and semi- (1,464 segmentation masks are available) supervised settings, which are the new state-of-the-arts