A technique for constructing a model supporting a plurality of domains is disclosed. In the technique, a plurality of teacher models, each of which is specialized for different one of the plurality of the domains, is prepared. A plurality of training data collections, each of which is collected for different one of the plurality of the domains, is obtained. A plurality of soft label sets is generated by inputting each training data in the plurality of the training data collections into corresponding one of the plurality of the teacher models. A student model is trained using the plurality of the soft label sets.

Novel tools and techniques are provided for implementing digital microscopy imaging using deep learning-based segmentation and/or implementing instance segmentation based on partial annotations. In various embodiments, a computing system might receive first and second images, the first image comprising a field of view of a biological sample, while the second image comprises labeling of objects of interest in the biological sample. The computing system might encode, using an encoder, the second image to generate third and fourth encoded images (different from each other) that comprise proximity scores or maps. The computing system might train an AI system to predict objects of interest based at least in part on the third and fourth encoded images. The computing system might generate (using regression) and decode (using a decoder) two or more images based on a new image of a biological sample to predict labeling of objects in the new image.

The present invention belongs to the technical field of computer vision, and provides a video semantic segmentation method based on active learning, comprising an image semantic segmentation module, a data selection module based on the active learning and a label propagation module. The image semantic segmentation module is responsible for segmenting image results and extracting high-level features required by the data selection module; the data selection module selects a data subset with rich information at an image level, and selects pixel blocks to be labeled at a pixel level; and the label propagation module realizes migration from image to video tasks and completes the segmentation result of a video quickly to obtain weakly-supervised data. The present invention can rapidly generate weakly-supervised data sets, reduce the cost of manufacture of the data and optimize the performance of a semantic segmentation network.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a future occupancy prediction for a region of an environment. In one aspect, a method comprises: receiving sensor data generated by a sensor system of a vehicle that characterizes an environment in a vicinity of the vehicle as of a current time point, wherein the sensor data comprises a plurality of sensor samples characterizing the environment that were each captured at different time points; processing a network input comprising the sensor data using a neural network to generate an occupancy prediction output for a region of the environment, wherein: the occupancy prediction output characterizes, for one or more future intervals of time after the current time point, a respective likelihood that the region of the environment will be occupied by an agent in the environment during the future interval of time.

A method for performing a computer-aided diagnosis (CAD) for universal lesion detection includes: receiving a medical image; processing the medical image to predict lesion proposals and generating cropped feature maps corresponding to the lesion proposals; for each lesion proposal, applying a plurality of lesion detection classifiers to generate a plurality of lesion detection scores, the plurality of lesion detection classifiers including a whole-body classifier and one or more organ-specific classifiers; for each lesion proposal, applying an organ-gating classifier to generate a plurality of weighting coefficients corresponding to the plurality of lesion detection classifiers; and for each lesion proposal, performing weight gating on the plurality of lesion detection scores with the plurality of weighting coefficients to generate a comprehensive lesion detection score.

Aspects of the invention include systems and methods that train a teacher neural network using labeled images to obtain a trained teacher neural network, each pixel of each of the labeled images being assigned a label that indicates one of a set of classifications. A method includes providing a set of unlabeled images to the trained teacher neural network to generate a set of soft-labeled images, each pixel of each of the soft-labeled images being assigned a soft label that indicates one of the set of classifications and an uncertainty value associated with the soft label, and training a student neural network with a subset of the labeled images and the set of soft-labeled images to obtain a trained student neural network. Student-labeled images are obtained from unlabeled images using the trained student neural network.

Systems, methods, and computer program products for performing semi-supervised contrastive learning of visual representations are provided. For example, the present disclosure provides systems and methods that leverage particular data augmentation schemes and a learnable nonlinear transformation between the representation and the contrastive loss to provide improved visual representations. Further, the present disclosure also provides improvements for semi-supervised contrastive learning. For example, computer-implemented method may include performing semi-supervised contrastive learning based on a set of one or more unlabeled training data, generating an image classification model based on a portion of a plurality of layers in a projection head neural network used in performing the contrastive learning, performing fine-tuning of the image classification model based on a set of one or more labeled training data, and after performing the fine-tuning, distilling the image classification model to a student model comprising a relatively smaller number of parameters than the image classification model.

A computing device classifies unclassified observations. A first batch of unclassified observation vectors and a first batch of classified observation vectors are selected. A prior regularization error value and a decoder reconstruction error value are computed. A first batch of noise observation vectors is generated. An evidence lower bound (ELBO) value is computed. A gradient of an encoder neural network model is computed, and the ELBO value is updated. A decoder neural network model and an encoder neural network model are updated. The decoder neural network model is trained. The target variable value is determined for each observation vector of the unclassified observation vectors based on an output of the trained decoder neural network model. The target variable value is output.

A task appropriateness determination apparatus includes a first learning unit causing artificial intelligence (AI) to learn image information of an index indicating a target object in a task appropriately completed state, an appropriate image provider providing an image possibly including the target object in the appropriately completed state and the index, a second learning unit causing the AI to detect an image where the index is present from the provided image after learning of the index, and learn image information of the target object in the image where the index is present, an image capturing unit capturing an image of a region including the target object and the index at least after the task, and a task appropriateness determiner determining that the task has been appropriately performed in response to detection by the AI of the target object roughly identical to the learned target object in the appropriately completed state.

Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform acts of providing a semi-supervised learning abstraction model that includes an API; receiving, via the API, pre-training parameters at least identifying (a) a first set of unlabeled images and (b) an encoder model selected from the plurality of encoder models; executing a pre-training procedure that trains the encoder model using the first set of unlabeled images; receiving, via the API, supervised training parameters at least identifying (a) a second set of labeled images and (b) the encoder model that is pre-trained using the pre-training procedure; executing a supervised training procedure that further trains the encoder model using the second set of labeled images; and storing a encoder model checkpoint for the encoder model. Other embodiments are disclosed herein.