Weakly supervised semantic segmentation(WSSS) is a challenging task, which only requires category information for segmentation prediction. Existing WSSS methods can be divided into two types: CNN-based and transformer-based, and the ways of generating pseudo labels are different. The former uses Class Activation Mapping(Cam)to generate pseudo labels, but there is a problem that the activated areas...Show More
With the profound changes in the form of warfare, full-time intelligence, surveillance, and reconnaissance have become key point in combat operations. In response to the time and space problems encountered by traditional reconnaissance methods, the Airborne Wide-Area Persistent Surveillance System (AWAPSS) came into being, which can support a larger range of real-time surveillance, with a combinat...Show More
Colorization is a challenging task of adding colors to a given grayscale image. Related palettes can keep better consistency of color in an image and provide sharper results. This paper presents a novel technique that based on input's uniform LBP texture to generate multiple color palettes, while other methods based on reference images, words, or other subjective elements. By combing the generated...Show More
