A system for simplified generation of systems for analysis of satellite images to geolocate one or more objects of interest. A plurality of training images labeled for a study object or objects with irrelevant features loaded into a preexisting feature identification subsystem causes automated generation of models for the study object. This model is used to parameterize pre-engineered machine learning elements that are running a preprogrammed machine learning protocol. Training images with the study are used to train object recognition filters. This filter is used to identify the study object in unanalyzed images. The system reports results in a requestor's preferred format.

Discussed herein are systems, devices, and methods for automatic target recognition based on a non-visible input image. A method can include providing, as input to a first machine learning (ML) model for object classification, pixel data of a non-visible image, the first ML model including an encoder from a second ML model, the second ML model trained to generate a visible image representation of an input non-visible image, and receiving, from the first ML model, data indicating one or more objects present in the non-visible image.

A sequence of images depicting an object is captured, e.g., by a camera at a point-of-sale terminal in a retail store. The object is identified, such as by a barcode or watermark that is detected from one or more of the images. Once the object's identity is known, such information is used in training a classifier (e.g., a machine learning system) to recognize the object from others of the captured images, including images that may be degraded by blur, inferior lighting, etc. In another arrangement, such degraded images are processed to identify feature points useful in fingerprint-based identification of the object. Feature points extracted from such degraded imagery aid in fingerprint-based recognition of objects under real life circumstances, as contrasted with feature points extracted from pristine imagery (e.g., digital files containing label artwork for such objects). A great variety of other features and arrangementssome involving designing classifiers so as to combat classifier copyingare also detailed.

A method, an apparatus and a program for automatic generation of secondary class annotations. The method comprises obtaining a plurality of images of an environment, each of which comprising objects in the environment. Some of the objects are annotated, while other objects are not. The method comprises aligning the plurality of images to a common coordinates system and computing a plurality of weighted images by adding weights to regions in the plurality of images that are associated with annotated objects to reduce significance of such regions. The method further comprises generating, based on the plurality of weighted images, a background model of the environment by determining for each region in the common coordinates system a statistical metric representing a visual feature of a background of the environment. The background model is then utilized to identify the non-annotated objects and adding an annotation for each identified object.

Embodiments of the present invention concern detecting Test-Time Evasion (TTE) attacks on neural network, particularly deep neural network (DNN), classifiers. The manner of detection is similar to that used to detect backdoors of a classifier whose training dataset was poisoned. Given knowledge of the classifier itself, the adversary subtly (even imperceptibly) perturbs their input to the classifier at test time in order to cause the class decision to change from a source class to a target class. For example, an image of a person who is unauthorized to access a resource can be modified slightly so that the classifier decides the image is that of an authorized person. The detector is based on employing a method (similar to that used to detect backdoors in DNNs) to discover different such minimal perturbations for each in a set of clean (correctly classified) samples, to change the sample's ground-truth (source) class to every other (target) class. For each (source, target) class pair, null distributions of the sizes of these perturbations are modeled. A test sample is similarly minimally perturbed by the detector from its decided-upon (target) class to every other (potential source) class. The p-values according to the corresponding null distributions of these test-sample perturbations are assessed using the corresponding nulls to decide whether the test sample is a TTE attack.

Systems and methods of the present disclosure provide an improved approach for open-set instance segmentation by identifying both known and unknown instances in an environment. For example, a method can include receiving sensor point cloud input data including a plurality of three-dimensional points. The method can include determining a feature embedding and at least one of an instance embedding, class embedding, and/or background embedding for each of the plurality of three-dimensional points. The method can include determining a first subset of points associated with one or more known instances within the environment based on the class embedding and the background embedding associated with each point in the plurality of points. The method can include determining a second subset of points associated with one or more unknown instances within the environment based on the first subset of points. The method can include segmenting the input data into known and unknown instances.

A mobile device can implement a neural network-based style transfer scheme to modify an image in a first style to a second style. The style transfer scheme can be configured to detect an object in the image, apply an effect to the image, and blend the image using color space adjustments and blending schemes to generate a realistic result image. The style transfer scheme can further be configured to efficiently execute on the constrained device by removing operational layers based on resources available on the mobile device.

An augmented reality processing method is provided for a terminal. The method includes: obtaining a plurality of frames of images, comprising a first image and a second image, which is a frame of an image immediately following the first image; obtaining a key point set of a first object in the first image; obtaining, through a neural network model, first pose key point sets respectively corresponding to a plurality of objects in the second image; determining a second pose key point set of the first object in the second image according to the key point set and a motion trend of the first object; using a target first pose key point set as a key point set of the first object in the second image; and generating an augmented information image according to the key point set of the first object in the second image.

Systems, methods, and computer programs disclosed herein relate to training of machine learning models on the basis of image training data with a limited number of labeled images.

System, methods, and other embodiments described herein relate to semi-supervised training of a depth model using a neural camera model that is independent of a camera type. In one embodiment, a method includes acquiring training data including at least a pair of training images and depth data associated with the training images. The method includes training the depth model using the training data to generate a self-supervised loss from the pair of training images and a supervised loss from the depth data. Training the depth model includes learning the camera type by generating, using a ray surface model, a ray surface that approximates an image character of the training images as produced by a camera having the camera type. The method includes providing the depth model to infer depths from monocular images in a device.