Beijing Baidu Netcom Science Technology Co., Ltd

Baidu Online Network Technology (beijing) Co., Ltd.

Beijing Baidu Netcom Science and Technology Co., Ltd.

Chenxia Li

Yuning Du

Yanjun Ma

Ruoyu Guo

Baohua Lai

Dianhai Yu

Guang Cheng Li

Shanshan Liu

Shufu Xie

Guoyi Liu

Qiwen Liu

Kai Wei

Provided is a lightweight model training method, an image processing method, a device and a medium. The lightweight model training method includes: acquiring first and second augmentation probabilities and a target weight adopted in an e-th iteration; performing data augmentation on a data set based on the first and second augmentation probabilities respectively, to obtain first and second data sets; obtaining a first output value of a student model and a second output value of a teacher model based on the first data set; obtaining a third output value and a fourth output value based on the second data set; determining a distillation loss function, a truth-value loss function and a target loss function; training the student model based on the target loss function; and determining a first augmentation probability or target weight to be adopted in an (e+1)-th iteration in a case of e is less than E.

Lightweight model training method, image processing method, electronic device, and storage medium

The present disclosure provides a vision processing and model training method, device, storage medium and program product. A specific implementation solution is as follows: establishing an image classification network with the same backbone network as the vision model, performing a self-monitoring training on the image classification network by using an unlabeled first data set; initializing a weight of a backbone network of the vision model according to a weight of a backbone network of the trained image classification network to obtain a pre-training model, the structure of the pre-training model being consistent with that of the vision model, and optimize the weight of the backbone network by using real data set in a current computer vision task scenario, so as to be more suitable for the current computer vision task; then, training the pre-training model by using a labeled second data set to obtain a trained vision model.

Vision processing and model training method, device, storage medium and program product

Embodiments of the present disclosure provide a method and device for labelling a point of interest, a computer device, and a storage medium. The method includes the following. Image data to be labelled is obtained. The image data includes an image to be labelled and a collection location of the image to be labelled. Feature extraction is performed on the image to be labelled to obtain a first image feature of the image to be labelled. A first reference image corresponding to the image to be labelled is determined based on a similarity between the first image feature and a second image feature corresponding to each reference image in an image library. The point of interest of the image to be labelled is labelled based on a category of the first reference image and the collection location of the image to be labelled.

Method and device for labeling point of interest

The present disclosure provides a method and for acquiring text data of a trademark image, a computer device and a non-transitory computer readable storage medium. The method includes the followings. A trademark database including one or more mappings among trademark feature information, trademark description information and trademark text information is established. A to-be-processed image including image description information is acquired. Trademark feature information corresponding to the to-be-processed image is determined. The trademark text information corresponding to the trademark feature information as the text data of the trademark image corresponding to the to-be-processed image according to the one or more mappings in the trademark database when the trademark description information corresponding to the trademark feature information corresponding to the to-be-processed image is contained in the image description information corresponding to the to-be-processed image.

Method and device for acquiring text data from trademark image, computer device and storage medium

Growing community of inventors

Beijing, China

Chenxia Li