The disclosure provides an adaptive self-learning method and an adaptive self-learning system. The adaptive self-learning method includes steps of inputting a first complex model and unlabeled data to an adaptive semi-supervised learning module and performing a pre-semi-supervised learning module to generate an average precision variation. If the average precision variation does not satisfy a condition value at any one time out of an inference count, the semi-supervised learning module is performed. After performing the semi-supervised learning module, the steps include performing a self-learning module for refining the target model, and then the trained target model is disposed to a site device. The site device deploys the trained target model to perform an object detection procedure.

Embodiments of the present invention provide a model generation method, an image classification method, a controller, and an electronic device. The model generation method comprises: constructing a convolutional neural network model for image classification, and dividing the convolutional neural network model into N modules in sequence, wherein each module comprises multiple adjacent layers in the neural network model, and N is an integer greater than 1; based on unlabeled training data, training first to (N-1)-th module to obtain parameters and models of the first module to the (N-1)-th module; and cascading the trained first to (N-1)-th modules with N-th module, and training the cascaded N modules by using labeled training data, to obtain the 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.

The present invention relates to a waste classification system based on vision-hyperspectral fusion data, including: a first learning data generation unit generating first learning data for a target object via a first artificial intelligence model trained using a hyperspectral image of waste acquired via a hyperspectral sensor; a second learning data generation unit generating second learning data for the target object via a second artificial intelligence model trained using a vision image of waste acquired via a vision camera; and a waste classification unit that performs waste classification for the target object by applying the first learning data and the second learning data to a third artificial intelligence model.

A framework for interpreting machine learning models is proposed that utilizes interpretability methods to determine the contribution of groups of input variables to the output of the model. Input variables are grouped based on dependencies with other input variables. The groups are identified by processing a training data set with a clustering algorithm. Once the groups of input variables are defined, scores related to each group of input variables for a given instance of the input vector processed by the model are calculated according to one or more algorithms. The algorithms can utilize group Partial Dependence Plot (PDP) values, Shapley Additive Explanations (SHAP) values, and Banzhaf values, and their extensions among others, and a score for each group can be calculated for a given instance of an input vector per group. These scores can then be sorted, ranked, and then combined into one hybrid ranking.

The processes fine-tune vision-language models (VLMs) on large-scale image caption datasets to amend VLM text feature vectors of attribute-neutral descriptions given attribute-neutralization lists, such that the attribute-neutral descriptions are equidistant to those of attribute-specific descriptions using annotation-free debiasing loss without using attribute labels. Feature vectors for attribute-neutral descriptions can be debiased, whereas the attribute-specific descriptions retain the original information. One or more attribute groups can be used for the attribute-neutralization. There can be more than one VLM, such as for different human languages or different human cultures where some biasing can want to be retained. The processes can be applied to any image group, such as objects, animals, plants, rocks, or other object types, where there is at least one attribute group that contains at least two attributes for neutralization.

Mechanisms are provided for performing machine learning (ML) training of a ML action recognition computer model which involves processing an original input dataset to generate an object feature bank comprising object feature data structures for a plurality of different objects. For an input video, a verb data structure and an original object data structure are generated and a candidate object feature data structure is selected from the object feature bank for generation of pseudo composition (PC) training data. The PC training data is generated based on the selected candidate object feature data structure and comprises a combination of the verb data structure and the candidate object feature data structure. The PC training data represents a combination of an action and an object not represented in the original input dataset. ML training of the ML action recognition computer model is performed based on an unseen combination comprising the PC training data.

A system for physiological motion measurement is provided. The system may acquire a reference image corresponding to a reference motion phase of an ROI and a target image of the ROI corresponding to a target motion phase, wherein the reference motion phase may be different from the target motion phase. The system may identify one or more feature points relating to the ROI from the reference image, and determine a motion field of the feature points from the reference motion phase to the target motion phase using a motion prediction model. An input of the motion prediction model may include at least the reference image and the target image. The system may further determine a physiological condition of the ROI based on the motion field.

The present invention relates to a hyperspectral image-based waste material discrimination system including: a hyperspectral data acquisition unit for acquiring hyperspectral data on a target object by determining an analysis region from a hyperspectral image of waste, acquired through a hyperspectral sensor; a semi-supervised learning processing model unit for generating integrated data by processing the hyperspectral data through a semi-supervised learning processing model; and a target object material discrimination unit for discriminating the material of the target object through a deep learning model on the basis of the integrated data.

Semantic fill techniques are described that support generating fill and editing images from semantic inputs. A user input, for example, is received by a semantic fill system that indicates a selection of a first region of a digital image and a corresponding semantic label. The user input is utilized by the semantic fill system to generate a guidance attention map of the digital image. The semantic fill system leverages the guidance attention map to generate a sparse attention map of a second region of the digital image. A semantic fill of pixels is generated for the first region based on the semantic label and the sparse attention map. The edited digital image is displayed in a user interface.

A method for performing predictive operations, the method comprising receiving a classification dataset comprising clock drawing images, generating, using a classifier, one or more classification outputs, the one or more classification outputs comprising one or more identifications of dementia or non-dementia for respective ones of clock drawing images. The classifier comprises one or more weights based on a latent space associated with a relevance factor variational autoencoder (RF-VAE). The RF-VAE comprises an encoder configured to generate the latent space. The RF-VAE comprises a decoder configured to generate reconstructions of the second one or more clock drawings based on the latent space. The latent space comprises one or more latent dimensions representative of one or more unique aspects of variation associated with the second one or more clock drawings. The one or more latent dimensions comprise minimal total correlation between the one or more latent dimensions and two dimensions.