Learning Multi-level Region Consistency with Dense Multi-label Networks for Semantic Segmentation
This work addresses a specific issue in semantic segmentation for computer vision applications, representing an incremental improvement by integrating a novel module into existing systems.
The paper tackled the problem of noisy and implausible predictions in semantic image segmentation by proposing a dense multi-label network module to enforce region consistency at multiple levels, resulting in improved performance as demonstrated through comprehensive experiments.
Semantic image segmentation is a fundamental task in image understanding. Per-pixel semantic labelling of an image benefits greatly from the ability to consider region consistency both locally and globally. However, many Fully Convolutional Network based methods do not impose such consistency, which may give rise to noisy and implausible predictions. We address this issue by proposing a dense multi-label network module that is able to encourage the region consistency at different levels. This simple but effective module can be easily integrated into any semantic segmentation systems. With comprehensive experiments, we show that the dense multi-label can successfully remove the implausible labels and clear the confusion so as to boost the performance of semantic segmentation systems.