Key Region Extraction Via Scene Classification Model

Key regions are the similar regions of the scenes of the same category and they are the crucial and explicable areas. In this paper, we extract the key regions from the satellite images. The proposed method transfers the model of scene classification and obtains the result without the segmentation labels. First, the features of each layer of current scene classification models are extracted to find the relationships of key regions and scene classification labels. Second, we reconstruct the images from the relative features to obtain end-to-end results. There are areas of similar features between the images of the same categories and no areas of different categories. Last, we design the masks to obtain the key regions from the end-to-end results. The experiments were conducted on a typical scene classification dataset. The experimental result demonstrates the feasibility of extracting key regions by scene classification without relabeling the dataset.