Systems and methods that receive as input microscopy images, extract features, and apply layers of processing units to compute one or more set of cellular phenotype features, corresponding to cellular densities and/or fluorescence measured under different conditions. The system is a neural network architecture having a convolutional neural network followed by a multiple instance learning (MIL) pooling layer. The system does not necessarily require any segmentation steps or per cell labels as the convolutional neural network can be trained and tested directly on raw microscopy images in real-time. The system computes class specific feature maps for every phenotype variable using a fully convolutional neural network and uses multiple instance learning to aggregate across these class specific feature maps. The system produces predictions for one or more reference cellular phenotype variables based on microscopy images with populations of cells.

A computer-implemented method, system, and computer program product are provided for activity recognition. The method includes receiving, by a processor, a plurality of videos, the plurality of videos including labeled videos and unlabeled videos. The method also includes extracting, by the processor with a feature extraction convolutional neural network (CNN), frame features for frames from each of the plurality of videos. The method additionally includes estimating, by the processor with a feature aggregation system, a vector representation for one of the plurality of videos responsive to the frame features. The method further includes classifying, by the processor, an activity from the vector representation. The method also includes controlling an operation of a processor-based machine to react in accordance with the activity.

A computer-implemented method, system, and computer program product are provided for activity recognition in a mobile device. The method includes receiving a plurality of unlabeled videos from one or more cameras. The method also includes generating a classified video for each of the plurality of unlabeled videos by classifying an activity in each of the plurality of unlabeled videos. The method additionally includes storing the classified video in a location in a memory designated for videos of the activity in each of the classified videos.

A computer-implemented method, system, and computer program product are provided for activity recognition in a surveillance system. The method includes receiving a plurality of unlabeled videos from one or more cameras. The method also includes classifying an activity in each of the plurality of unlabeled videos. The method additionally includes controlling an operation of a processor-based machine to react in accordance with the activity.

The embodiments of the present disclosure provide an image processing method, and a processing device. The image processing method comprises: acquiring a first image including N components, where N is a positive integer greater than or equal to 1; and performing image conversion processing on the first image using a generative neural network, to output a first output image, wherein the generative neural network is trained using a Laplace transform function.

An information processing apparatus performs estimation processing on supervised data, and stores a relationship between teacher information and an estimation result. When unsupervised data is input, the information processing apparatus searches for supervised data high in degree of similarity in estimation result to unsupervised data, and generates teacher information from an estimation result of unsupervised data based on a relationship between teacher information and an estimation result about the detected supervised data.

In one embodiment, a method includes receiving an image on a computing device. The computing device may further execute a weakly-supervised classification algorithm to determine whether a target feature is present in the received image. As an example, the weakly-supervised classification algorithm may determine whether a building is depicted in the received image. In response to determining that a target feature is present, the method further includes using a weakly-supervised segmentation algorithm of the convoluted neural network to segment the received image for the target feature. Based on a determined footprint size of the target feature, a distribution of statistical information over the target feature in the image can be calculated.

A computer-implemented method and systems are provided for performing machine learning for an image classification task. The method includes selecting, by a processor operatively coupled to one or more databases, a first and a second image from one or more training sets in the one or more databases. The method further includes overlaying, by the processor, the second image on the first image to form a mixed image, by averaging an intensity of each of a plurality of co-located pixel pairs in the first and the second image. The method also includes training, by the processor, a machine learning process configured for the image classification task using the mixed image to augment data used by the machine learning process for the image classification task.

A computer-implemented method and systems are provided for performing machine learning for an image classification task. The method includes selecting, by a processor operatively coupled to one or more databases, a first and a second image from one or more training sets in the one or more databases. The method further includes overlaying, by the processor, the second image on the first image to form a mixed image, by averaging an intensity of each of a plurality of co-located pixel pairs in the first and the second image. The method also includes training, by the processor, a machine learning process configured for the image classification task using the mixed image to augment data used by the machine learning process for the image classification task.

Generating soft labels used for training a unified model is achieved by unification of models having respective target classes with distillation. A collection of samples is prepared. Predictions are generated by individual trained models. Individual trained models have an individual class set to form a unified class set that includes target classes. The unified soft labels are estimated for each sample over the target classes in the unified class set from the predictions using a relation connecting a first output of each individual trained model and a second output of the unified model. The unified soft labels are output to train a unified model having the unified class set.