Abstract: A parallel data access method for massive remote-sensing images includes: 1) segmenting a remote-sensing image to be processed using a set grid system, data in each grid corresponding to a data block; 2) collecting a data access log of an underlying distributed object storage system Ceph in a past period of time, and measuring a load index of each Ceph cluster and a load index of each pool; 3) selecting a pool with a minimum load in a Ceph cluster with a minimum current load to serve as a storage position of a current data block, and writing each data block into a corresponding pool; 4) returning a data identifier dataid and a data access path of the remote-sensing image; and 5) storing metadata of each data block in a metadata database. The method can support rapid and high-concurrency read and write of large-area data of a grid data block.

Abstract: Example embodiments of aspects of the present disclosure provide an example computer-implemented method for improved prompting of a machine-learned model. The example method can include obtaining an instructive sequence descriptive of an instructive query, an instructive response, and an instructive trace of intermediate states from the instructive query to the instructive response. The example method can include inputting, to a machine-learned model, the instructive sequence and an operative query, wherein the machine-learned model is configured to process the operative query with attention over the instructive sequence. The example method can include generating, using the machine-learned model and responsive to the operative query, an operative response.

Abstract: Provided are a beauty processing method and apparatus. The method includes: obtaining an original face image, and extracting original parameter information corresponding to a site feature of a to-be-beautified site; determining, based on the original parameter information, a site beauty parameter corresponding to the to-be-beautified site; and processing the to-be-beautified site based on the site beauty parameter to generate a target face image. Thus, the personalized beauty parameters can be generated to meet the user's personalized beauty needs, improving the accuracy of the beauty parameter and enhancing the beauty effect.

Abstract: An example method for pretraining a machine-learned model is provided. The example method includes obtaining a plurality of different combinations of configuration parameters of a pretraining objective framework. The example method includes generating, using the pretraining objective framework, a plurality of corrupted training examples from one or more training examples, wherein the plurality of corrupted training examples are respectively generated according to the plurality of different combinations. The example method includes inputting the plurality of corrupted training examples into the machine-learned model, wherein the machine-learned model is configured to generate uncorrupted subportions corresponding to corrupted subportions of the corrupted training examples. The example method includes obtaining, from the machine-learned model, a plurality of outputs respectively generated by the machine-learned model based on the plurality of corrupted training examples.

Abstract: Provided are a beauty processing method and apparatus. The method includes: obtaining an original face image, and extracting original parameter information corresponding to a site feature of a to-be-beautified site; determining, based on the original parameter information, a site beauty parameter corresponding to the to-be-beautified site; and processing the to-be-beautified site based on the site beauty parameter to generate a target face image. Thus, the personalized beauty parameters can be generated to meet the user's personalized beauty needs, improving the accuracy of the beauty parameter and enhancing the beauty effect.

Abstract: A parallel data access method for massive remote-sensing images includes: 1) segmenting a remote-sensing image to be processed using a set grid system, data in each grid corresponding to a data block; 2) collecting a data access log of an underlying distributed object storage system Ceph in a past period of time, and measuring a load index of each Ceph cluster and a load index of each pool; 3) selecting a pool with a minimum load in a Ceph cluster with a minimum current load to serve as a storage position of a current data block, and writing each data block into a corresponding pool; 4) returning a data identifier dataid and a data access path of the remote-sensing image; and 5) storing metadata of each data block in a metadata database. The method can support rapid and high-concurrency read and write of large-area data of a grid data block.

Abstract: Example aspects of the present disclosure are directed to systems and methods for performing automatic label smoothing of augmented training data. In particular, some example implementations of the present disclosure which in some instances can be referred to “AutoLabel” can automatically learn the labels for augmented data based on the distance between the clean distribution and augmented distribution. AutoLabel is built on label smoothing and is guided by the calibration-performance over a hold-out validation set. AutoLabel is a generic framework that can be easily applied to existing data augmentation methods, including AugMix, mixup, and adversarial training, among others. AutoLabel can further improve clean accuracy, as well as the accuracy and calibration over corrupted datasets. Additionally, AutoLabel can help adversarial training by bridging the gap between clean accuracy and adversarial robustness.