Abstract: Systems and methods are provided for reusing and retraining an image recognition model for video analytics. The image recognition model is used for inferring a frame of video data that is captured at edge devices. The edge devices periodically or under predetermined conditions transmits a captured frame of video data to perform inferencing. The disclosed technology is directed to select an image recognition model from a model store for reusing or for retraining. A model selector uses a gating network model to determine ranked candidate models for validation. The validation includes iterations of retraining the image recognition model and stopping the iteration when a rate of improving accuracy by retraining becomes smaller than the previous iteration step. Retraining a model includes generating reference data using a teacher model and retraining the model using the reference data. Integrating reuse and retraining of models enables improvement in accuracy and efficiency.

Abstract: Systems and methods are provided for continuous learning of models across hierarchies under a multi-access edge computing. In particular, an on-premises edge server, using a model, generates inference data associated with captured stream data. A data drift determiner determines a data drift in the inference data by comparing the data against reference data generated using a golden model. The data drift indicates a loss of accuracy in the inference data. A gateway model maintains one or more models in a model cache for update the model. The gateway model instructs the one or more servers to train the new model. The gateway model transmits the trained model to update the model in the on-premises edge server. Training the new model includes determining an on-premises edge server with computing resources available to train the new model while generating other inference data for incoming stream data in the data analytic pipeline.

Abstract: A cloud-based service uses an offline training pipeline to categorize training data for machine learning (ML) models into various clusters. Incoming test data that is received by a data center or in a cloud environment is compared against the categorized training data to identify the appropriate ML model to assign the test data. The comparison of the test data is done in real-time using a similarity metric that takes into account spatial and temporal factors of the test data relative to the categorized training data.

Abstract: A method can include classifying, using a compressed and specialized convolutional neural network (CNN), an object of a video frame into classes, clustering the object based on a distance of a feature vector of the object to a feature vector of a centroid object of the cluster, storing top-k classes, a centroid identification, and a cluster identification, in response to receiving a query for objects of class X from a specific video stream, retrieving image data for each centroid of each cluster that includes the class X as one of the top-k classes, classifying, using a ground truth CNN (GT-CNN), the retrieved image data for each centroid, and for each centroid determined to be classified as a member of the class X providing image data for each object in each cluster associated with the centroid.

Abstract: A method can include classifying, using a compressed and specialized convolutional neural network (CNN), an object of a video frame into classes, clustering the object based on a distance of a feature vector of the object to a feature vector of a centroid object of the cluster, storing top-k classes, a centroid identification, and a cluster identification, in response to receiving a query for objects of class X from a specific video stream, retrieving image data for each centroid of each cluster that includes the class X as one of the top-k classes, classifying, using a ground truth CNN (GT-CNN), the retrieved image data for each centroid, and for each centroid determined to be classified as a member of the class X providing image data for each object in each cluster associated with the centroid.

Abstract: A method can include classifying, using a compressed and specialized convolutional neural network (CNN), an object of a video frame into classes, clustering the object based on a distance of a feature vector of the object to a feature vector of a centroid object of the cluster, storing top-k classes, a centroid identification, and a cluster identification, in response to receiving a query for objects of class X from a specific video stream, retrieving image data for each centroid of each cluster that includes the class X as one of the top-k classes, classifying, using a ground truth CNN (GT-CNN), the retrieved image data for each centroid, and for each centroid determined to be classified as a member of the class X providing image data for each object in each cluster associated with the centroid.

Abstract: A method can include classifying, using a compressed and specialized convolutional neural network (CNN), an object of a video frame into classes, clustering the object based on a distance of a feature vector of the object to a feature vector of a centroid object of the cluster, storing top-k classes, a centroid identification, and a cluster identification, in response to receiving a query for objects of class X from a specific video stream, retrieving image data for each centroid of each cluster that includes the class X as one of the top-k classes, classifying, using a ground truth CNN (GT-CNN), the retrieved image data for each centroid, and for each centroid determined to be classified as a member of the class X providing image data for each object in each cluster associated with the centroid.