In addition, only the foreground categories are considered.

The success of the Segment Anything Model (SAM) demonstrates the significance of data-centric machine learning. However, due to the difficulties and high costs associated with annotating Remote Sensing (RS) images, a large amount of valuable RS data remains unlabeled, particularly at the pixel level. In this study, we leverage SAM and existing RS object detection datasets to develop an efficient pipeline for generating a large-scale RS segmentation dataset, dubbed SAMRS. SAMRS totally possesses 105,090 images and 1,668,241 instances, surpassing existing high-resolution RS segmentation datasets in size by several orders of magnitude. It provides object category, location, and instance information that can be used for semantic segmentation, instance segmentation, and object detection, either individually or in combination. We also provide a comprehensive analysis of SAMRS from various aspects. Moreover, preliminary experiments highlight the importance of conducting segmentation pre-training with SAMRS to address task discrepancies and alleviate the limitations posed by limited training data during fine-tuning.

The success of the Segment Anything Model (SAM) demonstrates the significance of data-centric machine learning. However, due to the difficulties and high costs associated with annotating Remote Sensing (RS) images, a large amount of valuable RS data remains unlabeled, particularly at the pixel level. In this study, we leverage SAM and existing RS object detection datasets to develop an efficient pipeline for generating a large-scale RS segmentation dataset, dubbed SAMRS. SAMRS totally possesses 105,090 images and 1,668,241 instances, surpassing existing high-resolution RS segmentation datasets in size by several orders of magnitude. It provides object category, location, and instance information that can be used for semantic segmentation, instance segmentation, and object detection, either individually or in combination.

Chinese tech giant Tencent has joined forces with the nation's National Astronomical Observatories to journey into AI space exploration, CEO Pony Ma told the 2021 World Artificial Intelligence Conference in Shanghai on Thursday. The forward-looking announcement came during a tough week for Chinese tech companies, as Beijing tightened data security and antitrust regulations. Tencent is best known for its WeChat messaging service and very healthy gaming arm, but also operates a decent cloud and increasingly invests in AI through its in-house AI research division YouTu Lab. The company will leverage the latter two capabilities to conduct AI analysis in hopes of finding evidence of pulsars among the 30 million signal images collected each week by China's 500-metre Aperture Spherical Radio Telescope (FAST). Tencent Vice-President Zhang Lijun reckons use of his company's facilities will reduce the time to process a week's worth of images from one year to three days.