Spatial pooling has been proven highly effective in capturing long-range contextual information for pixel-wise prediction tasks, such as scene parsing.
We turn it into a realistic few-shot classification benchmark by splitting the object categories into head and tail based on their distribution in the world.
On the other hand, feature fusion modules are designed to combine different modal of semantic features, which leverage the information from both inputs for better accuracy.
Drones or general Unmanned Aerial Vehicles (UAVs), endowed with computer vision function by on-board cameras and embedded systems, have become popular in a wide range of applications.
On the one hand, the integrated classification model contains multiple classifiers, not only the general classifier but also a refinement classifier to distinguish the confusing categories.
In this paper, we investigate a novel deep-model reusing task.
Semantic segmentation generates comprehensive understanding of scenes through densely predicting the category for each pixel.
#11 best model for Semantic Segmentation on Cityscapes test
Scene understanding of high resolution aerial images is of great importance for the task of automated monitoring in various remote sensing applications.