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 arrangements—some involving designing classifiers so as to combat classifier copying—are also detailed.

A system includes a K1 preprocessing module designed to generate at least one intermediate image from an input image using a parameterized internal processing chain and an analysis module to detect a feature or object in the intermediate image. A method to train the system includes feeding a plurality of learning input images to the system, comparing a result provided by the analysis module for each of the learning input images to a learning value, and feeding back a deviation obtained by the comparison to an input preprocessing module and/or adapting parameters of the internal processing chain to reduce the deviation.

A machine-learning classification system includes a first machine-learning classifier that classifies each element of a plurality of data items to generate a plurality of classified data items. A second machine-learning classifier identifies misclassified elements of the plurality of classified data items and reclassifies each of the identified misclassified elements to generate a plurality of reclassified data items. A second machine-learning classifier identifies unclassified elements of the plurality of classified data items and classifies each of the identified unclassified elements to generate a plurality of reclassified data items. An ensemble classifier adjusts the classifications of the elements of the plurality of classified data items in response to the plurality of reclassified data items and the plurality of newly-classified elements.

A previously trained classification model associated with the machine learning system is configured to process an input to generate i) a first prediction that represents a characteristic associated with the input, and ii) a representation of accuracy associated with the prediction. A retraining subsystem is configured to receive the input, the first prediction, and the representation of accuracy. The retraining subsystem processes the input to generate a prediction representing a characteristic. A sufficiency of certainty of the first prediction is determined based on at least the input, the first prediction, the measure of accuracy, and the second prediction. Based at least on the determined sufficiency the retraining subsystem causes the machine learning system to be automatically retrained, be retrained using the input with active learning or not retrained.

In some embodiments, aerial images of a geographic area are captured by an autonomous vehicle. In some embodiments, the locations of structures within a subset of the aerial images are manually annotated, and geographical locations of the manual annotations are determined based on pose information of the camera. In some embodiments, a machine learning model is trained using the manually annotated aerial images. The machine learning model is used to automatically generate annotations of other images of the geographic area, and the geographical locations determined from the manual annotations are used to determine an accuracy probability of the automatic annotations. The automatic annotations determined to be accurate may be used to re-train the machine learning model to increase its precision and recall.

A system and methods are provided in which an artificial intelligence inference module identifies targeted information in large-scale unlabeled data, wherein the artificial intelligence inference module autonomously learns hierarchical representations from large-scale unlabeled data and continually self-improves from self-labeled data points using a teacher model trained to detect known targets from combined inputs of a small hand labeled curated dataset prepared by a domain expert together with self-generated intermediate and global context features derived from the unlabeled dataset by unsupervised and self-supervised processes. The trained teacher model processes further unlabeled data to self-generate new weakly-supervised training samples that are self-refined and self-corrected, without human supervision, and then used as inputs to a noisy student model trained in a semi-supervised learning process on a combination of the teacher model training set and new weakly-supervised training samples. With each iteration, the noisy student model continually self-optimizes its learned parameters against a set of configurable validation criteria such that the learned parameters of the noisy student surpass and replace the learned parameter of the prior iteration teacher model, with these optimized learned parameters periodically used to update the artificial intelligence inference module.

This disclosure includes computer vision technologies for image categorization, such as used for product recognition. In one embodiment, the disclosed system uses a channel interaction network to learn stronger fine-grained features and to distinguish the subtle differences between two similar images. Additionally, the disclosed channel interaction network may be integrated into an existing feature extractor network to boost its performance for image categorization.

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.

A learning-based model is trained using a plurality of attributes of media. Depth estimation is performed using the learning-based model. The depth estimation supports performing a computer vision task on the media. Attributes used in the depth estimation include scene understanding, depth correctness, and processing of sharp edges and gaps. The media may be processed to perform media restoration or the media quality enhancement. A computer vision task may include semantic segmentation.

An example system includes a processor to receive an image containing an object to be detected. The processor is to detect the object in the image via a binary object detector trained via a self-supervised training on raw and unlabeled videos.