A method for training an instance segmentation model. The method includes: providing unlabeled images and labeled images representing labeled objects; generating a first image by including one or more of the labeled objects into an unlabeled image, generating a second image by including one or more additional labeled objects into the first image and/or removing at least one of the one or more labeled objects from the first image, generating a third image by spatially augmenting the first image; training the model by: generating a first, second, and third prediction, by inputting the first image, the second image, and the third image, respectively, into the model; determining an embedding loss of the first prediction and the second prediction, determining a regularization loss of the first prediction and the third prediction, wherein the first prediction represents pseudo-labels, and training the model using the embedding loss and the regularization loss.

Systems and methods for annotating and tracking objects in a video are described herein. The methods include operating at least one processor to: receive, from at least one image device proximal to the manufacturing device, a sequence of frames of a video showing the plurality of parts within the manufacturing device; receive at least one annotated frame having labelling of a subset of parts of the plurality of parts in a plurality of frames of the video, the annotated frame being video annotation data; apply the video annotation data as input to a propagation algorithm to annotate an additional subset of parts of the plurality of parts within the frames of the video, the additional annotated frames being additional video annotation data; apply a segmentation model to the additional video annotation data to generate image segmentation masks of each of the parts, the image segmentation masks being trained segmentation model output data; and apply an object detection model to the trained segmentation model output tracking data to get a fine-tuned object detection model to detect and track the parts.

This invention provides a model generation method, an object detection method, a controller, and an electronic device. The model generation method comprises: constructing a convolutional neural network model used for multi-scale object detection, and dividing the convolutional neural network model into a plurality of modules, the plurality of modules comprising a feature extraction module and a plurality of detection head modules of different scales; using unlabeled training data to pre-train the feature extraction module to obtain parameters and models of the feature extraction module; and connecting the trained feature extraction module to the plurality of detection head modules respectively, and using labeled training data to train a plurality of the modules which have been connected, to obtain parameters and models of the modules. A high-precision convolutional neural network model can be obtained without the need to label a large amount of training data, and the labor and time required for labeling the training data are saved.

A data processing service generates synthetic captions for uncaptioned images of a set of training data. The data processing service applies a pre-trained I2T model to the uncaptioned images, generating synthetic captions as output. The data processing service uses the training data to train a T2I model to produce images from text.

Methods and systems for determining information for a specimen are provided. One system includes a computer system and one or more components executed by the computer system. The one or more components include a pre-trained vision foundation model (VFM) configured for projecting multiple images for a specimen to high dimensional embeddings via continuous pretraining. The multiple images include an image generated for the specimen with one or more modes of an imaging system. The one or more components also include one or more additional components configured for determining information for the specimen from the high dimensional embeddings.

Apparatuses, systems, and techniques to detect object in images including digital representations of those objects. In at least one embodiment, one or more objects are detected in an image based, at least in part, on one or more pseudo-labels corresponding to said one or more objects.

Disclosed is a method comprising receiving a telecommunication signal (211) that is attenuated in multiple different weather conditions; labeling the telecommunication signal (211) with the multiple different weather conditions; generating a set of spectrogram images (221-229) based on the telecommunication signal labeled with the multiple different weather conditions; and training a deep learning model (240) for detecting and classifying the multiple different weather conditions based on the set of spectrogram images (221-229).

A storage medium storing a training processing program that causes at least one computer to execute a process that includes acquiring a deviation degree of a feature in a training dataset, by using a determination model, the training dataset being unlabeled; selecting one or more pieces of data included in the training dataset based on the deviation degree; outputting the selected one or more pieces of data or related data related to the selected one or more pieces of data; receiving an input of a determination result by a user for the one or more pieces of data; and determining an adjustment standard used to adjust a feature of each piece of the data included in the training dataset based on the received determination result, wherein when determination target data is determined by the determination model, a feature of the determination target data is adjusted based on the adjustment standard.

A data classification and recognition method includes: obtaining a first data set and a second data set, the second data set including second data, samples in the second data being labeled; performing training using first data in an unsupervised training mode and using the second data in a supervised training mode to obtain a first classification model; obtaining a second classification model; performing distillation training on a model parameter of the second classification model to obtain a data classification model; and performing class prediction on target data by using the data classification model.

Apparatuses, systems, and techniques to identify objects within an image. In at least one embodiment, objects are identified in an image using one or more neural networks based, at least in part, on neural network outputs ranked according to uncertainty values.