CVPR2018

Institute: UIUC, NUS, IBM, Tencent URL:https://arxiv.org/pdf/1805.04574.pdf Keyword: Weakly Supervised Semantic Segmentation Interest: 2

Simble is best #Result is good

[Problem] We obverse the performance gap mainly comes from their limitation on learning to produce highquality dense object localization maps from image-level supervision.
[How to do] 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.
[Result] it achieves 60.8% and 67.6% mIoU scores on Pascal VOC 2012 test set in weakly- (only image-level labels are available) and semi- (1,464 segmentation masks are available) supervised settings, which are the new state of-the-arts.