The effect of scene context on weakly supervised semantic segmentation

no code implementations • 12 Feb 2019 • Mohammad Kamalzare, Reza Kahani, Alireza Talebpour, Ahmad Mahmoudi-Aznaveh

More specifically, some objects which are commonly seen in one specific scene (e. g. 'train' typically is seen on 'railroad track') are much more likely to be confused.

Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation