A method and apparatus are provided. The method includes receiving an image, detecting an object in the image, determining, by a primary object detector, a primary confidence detection score of the object, determining, by a classification network, a confidence scaling factor of the object, and adjusting the primary confidence detection score based on multiplying the primary confidence detection score by the confidence scaling factor.

System and method for deep network fusion for fast and robust object detection

Improved techniques for training a machine learning (ML) model are discussed herein. Training the ML model can be based on a subset of examples. In particular, the training can include identifying a reference region associated with an area of the image representing an object, and selecting, based at least in part on a first confidence score associated with a first bounding box, a first hard example for inclusion in the subset of examples. In some cases, the first confidence score and the first bounding box can be associated with a first portion of the feature map. Next, the training can include determining that a first degree of alignment of the first bounding box to the reference region is above a threshold degree of alignment, and in response, replacing the first hard example with a second hard example.

Machine learning techniques

In an example embodiment, a first DCNN is trained to output a value for a first metric by inputting a plurality of sample documents to the first DCNN, with each of the sample documents having been labeled with a value for the first metric. Then a plurality of possible transformations of a first input document are fed to the fi rst DCNN, obtaining a value for the fi rst metric for each of the plurality of possible transformations. A first transformation is selected from the plurality of possible transformations based on the values for the first metric for each of the plurality of possible transformations. Then a second DCNN is trained to output a transformation for a document by inputting the selected first transformation to the second DCNN. The second input document is fed to the second DCNN, obtaining a second transformation of the second input document.

Training a neural network using another neural network

The shop identification method based on street view of the disclosed embodiment belongs to the computer technical field and is helpful to improve the efficiency of determining the shop state. A methodfor identifying a store based on street view provide by an embodiment of that present disclosure includes acquiring street view information collected by a street view information collection device, wherein the street view information include at least a geographic position and a street view image; acquiring a first store image in the street view image; according to the geographic position, the acquired first store image is matched with the second store image in the preset store image set, and the operation state of the corresponding store is determined according to the matching result. The store identification method based on street view provided by the embodiment of the present disclosure improves the efficiency of determining the state of a store by using a store image collected by a street view information collection device and identifying a store based on multimodal features such as geographical location and store image features.

Street view-based store identification method, device, electronic device and storage medium

Instance segmentation inferred from machine learning model output

Aspects of the present disclosure relate to a method includes training a deep neural network using training images and data identifying one or more business storefront locations in the training images The deep neural network outputs tight bounding boxes on each image At the deep neural network, a first image may be received The first image may be evaluated using the deep neural network Bounding boxes may then be generated identifying business storefront locations in the first image

Yu Qian

Papers

Business discovery from imagery