Abstract: Embodiments are disclosed for finding similar persons in images. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an image query, the image query including an input image that includes a representation of a person, generating a first cropped image including a representation of the person's face and a second cropped image including a representation of the person's body, generating an image embedding for the input image by combining a face embedding corresponding to the first cropped image and a body embedding corresponding to the second cropped image, and querying an image repository in embedding space by comparing the image embedding to a plurality of image embeddings associated with a plurality of images in the image repository to obtain one or more images based on similarity to the input image in the embedding space.

Abstract: The present disclosure relates to an object selection system that automatically detects and selects objects in a digital image based on natural language-based inputs. For instance, the object selection system can utilize natural language processing tools to detect objects and their corresponding relationships within natural language object selection queries. For example, the object selection system can determine alternative object terms for unrecognized objects in a natural language object selection query. As another example, the object selection system can determine multiple types of relationships between objects in a natural language object selection query and utilize different object relationship models to select the requested query object.

Abstract: Systems and methods for image processing are described. One or more embodiments of the present disclosure identify a latent vector representing an image of a face, identify a target attribute vector representing a target attribute for the image, generate a modified latent vector using a mapping network that converts the latent vector and the target attribute vector into a hidden representation having fewer dimensions than the latent vector, wherein the modified latent vector is generated based on the hidden representation, and generate a modified image based on the modified latent vector, wherein the modified image represents the face with the target attribute.

Abstract: The present disclosure relates to an object selection system that accurately detects and automatically selects target instances of user-requested objects (e.g., a query object instance) in a digital image. In one or more embodiments, the object selection system can analyze one or more user inputs to determine an optimal object attribute detection model from multiple specialized and generalized object attribute models. Additionally, the object selection system can utilize the selected object attribute model to detect and select one or more target instances of a query object in an image, where the image includes multiple instances of the query object.

Abstract: Methods, systems, and non-transitory computer readable media are disclosed for accurately and efficiently generating groups of images portraying semantically similar objects for utilization in building machine learning models. In particular, the disclosed system utilizes metadata and spatial statistics to extract semantically similar objects from a repository of digital images. In some embodiments, the disclosed system generates color embeddings and content embeddings for the identified objects. The disclosed system can further group similar objects together within a query space by utilizing a clustering algorithm to create object clusters and then refining and combining the object clusters within the query space. In some embodiments, the disclosed system utilizes one or more of the object clusters to build a machine learning model.

Abstract: This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that extract multiple attributes from an object portrayed in a digital image utilizing a multi-attribute contrastive classification neural network. For example, the disclosed systems utilize a multi-attribute contrastive classification neural network that includes an embedding neural network, a localizer neural network, a multi-attention neural network, and a classifier neural network. In some cases, the disclosed systems train the multi-attribute contrastive classification neural network utilizing a multi-attribute, supervised-contrastive loss. In some embodiments, the disclosed systems generate negative attribute training labels for labeled digital images utilizing positive attribute labels that correspond to the labeled digital images.

Abstract: A panoptic labeling system includes a modified panoptic labeling neural network (“modified PLNN”) that is trained to generate labels for pixels in an input image. The panoptic labeling system generates modified training images by combining training images with mask instances from annotated images. The modified PLNN determines a set of labels representing categories of objects depicted in the modified training images. The modified PLNN also determines a subset of the labels representing categories of objects depicted in the input image. For each mask pixel in a modified training image, the modified PLNN calculates a probability indicating whether the mask pixel has the same label as an object pixel. The modified PLNN generates a mask label for each mask pixel, based on the probability. The panoptic labeling system provides the mask label to, for example, a digital graphics editing system that uses the labels to complete an infill operation.

Abstract: Semantic segmentation techniques and systems are described that overcome the challenges of limited availability of training data to describe the potentially millions of tags that may be used to describe semantic classes in digital images. In one example, the techniques are configured to train neural networks to leverage different types of training datasets using sequential neural networks and use of vector representations to represent the different semantic classes.

Abstract: Methods and systems are provided for accurately filling holes, regions, and/or portions of images using iterative image inpainting. In particular, iterative inpainting utilize a confidence analysis of predicted pixels determined during the iterations of inpainting. For instance, a confidence analysis can provide information that can be used as feedback to progressively fill undefined pixels that comprise the holes, regions, and/or portions of an image where information for those respective pixels is not known. To allow for accurate image inpainting, one or more neural networks can be used. For instance, a coarse result neural network (e.g., a GAN comprised of a generator and a discriminator) and a fine result neural network (e.g., a GAN comprised of a generator and two discriminators).

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for detecting and classifying an exposure defect in an image using neural networks trained via a limited amount of labeled training images. An image may be applied to a first neural network to determine whether the images includes an exposure defect. Detected defective image may be applied to a second neural network to determine an exposure defect classification for the image. The exposure defect classification can includes severe underexposure, medium underexposure, mild underexposure, mild overexposure, medium overexposure, severe overexposure, and/or the like. The image may be presented to a user along with the exposure defect classification.

Abstract: Systems and methods for image tagging are described. In some embodiments, images with problematic tags are identified after applying an auto-tagger. The images with problematic tags are then sent to an object detection network. In some cases, the object detection network is trained using a training set selected to improve detection of objects associated with the problematic tags. The output of the object detection network can be merged with the output of the auto-tagger to provide a combined image tagging output. In some cases, the output of the object detection network also includes a bounding box, which can be used to crop the image around a relevant object so that the auto-tagger can be reapplied to a portion of the image.

Abstract: This disclosure describes one or more implementations of a digital image semantic layout manipulation system that generates refined digital images resembling the style of one or more input images while following the structure of an edited semantic layout. For example, in various implementations, the digital image semantic layout manipulation system builds and utilizes a sparse attention warped image neural network to generate high-resolution warped images and a digital image layout neural network to enhance and refine the high-resolution warped digital image into a realistic and accurate refined digital image.

Abstract: The present disclosure relates to an object selection system that accurately detects and automatically selects target instances of user-requested objects (e.g., a query object instance) in a digital image. In one or more embodiments, the object selection system can analyze one or more user inputs to determine an optimal object attribute detection model from multiple specialized and generalized object attribute models. Additionally, the object selection system can utilize the selected object attribute model to detect and select one or more target instances of a query object in an image, where the image includes multiple instances of the query object.

Abstract: The present disclosure relates to an object selection system that automatically detects and selects objects in a digital image based on natural language-based inputs. For instance, the object selection system can utilize natural language processing tools to detect objects and their corresponding relationships within natural language object selection queries. For example, the object selection system can determine alternative object terms for unrecognized objects in a natural language object selection query. As another example, the object selection system can determine multiple types of relationships between objects in a natural language object selection query and utilize different object relationship models to select the requested query object.

Abstract: A low-computation underwater acoustic wake-up method based on a multi-carrier signal is provided. A multi-carrier signal corresponding to communication nodes is constructed, absolute values of the multi-carrier signal in a window at a receiver are summed for signal arrival detection, and then frequency points of the multi-carrier signal are detected many times by using the real fast Fourier transform to realize wake-up detection. The method is suitable for accurate wake-up at any distance within a maximum communication distance of two underwater acoustic nodes, has a small amount of calculation, and is suitable for low-power single-chip microcomputers. The modem can be in a low-power sleep state for a long time.

Abstract: A distractor detector includes a heatmap network and a distractor classifier. The heatmap network operates on an input image to generate a heatmap for a main subject, a heatmap for a distractor, and optionally a heatmap for the background. Each object is cropped within the input image to generate a corresponding cropped image. Regions within the heatmaps that correspond to the objects are identified, and each of the regions is cropped within each of the heatmaps to generate cropped heatmaps. The distractor classifier then operates on the cropped images and the cropped heatmaps to classify each of the objects as being either a main subject or a distractor.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for generating semantic scene graphs for digital images using an external knowledgebase for feature refinement. For example, the disclosed system can determine object proposals and subgraph proposals for a digital image to indicate candidate relationships between objects in the digital image. The disclosed system can then extract relationships from an external knowledgebase for refining features of the object proposals and the subgraph proposals. Additionally, the disclosed system can generate a semantic scene graph for the digital image based on the refined features of the object/subgraph proposals. Furthermore, the disclosed system can update/train a semantic scene graph generation network based on the generated semantic scene graph. The disclosed system can also reconstruct the image using object labels based on the refined features to further update/train the semantic scene graph generation network.

Abstract: Embodiments are disclosed for finding similar persons in images. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an image query, the image query including an input image that includes a representation of a person, generating a first cropped image including a representation of the person's face and a second cropped image including a representation of the person's body, generating an image embedding for the input image by combining a face embedding corresponding to the first cropped image and a body embedding corresponding to the second cropped image, and querying an image repository in embedding space by comparing the image embedding to a plurality of image embeddings associated with a plurality of images in the image repository to obtain one or more images based on similarity to the input image in the embedding space.

Abstract: Systems and techniques are described that provide for generalizable approach policy learning and implementation for robotic object approaching. Described techniques provide fast and accurate approaching of a specified object, or type of object, in many different environments. The described techniques enable a robot to receive an identification of an object or type of object from a user, and then navigate to the desired object, without further control from the user. Moreover, the approach of the robot to the desired object is performed efficiently, e.g., with a minimum number of movements. Further, the approach techniques may be used even when the robot is placed in a new environment, such as when the same type of object must be approached in multiple settings.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately, efficiently, and flexibly generating modified digital images utilizing a guided inpainting approach that implements a patch match model informed by a deep visual guide. In particular, the disclosed systems can utilize a visual guide algorithm to automatically generate guidance maps to help identify replacement pixels for inpainting regions of digital images utilizing a patch match model. For example, the disclosed systems can generate guidance maps in the form of structure maps, depth maps, or segmentation maps that respectively indicate the structure, depth, or segmentation of different portions of digital images. Additionally, the disclosed systems can implement a patch match model to identify replacement pixels for filling regions of digital images according to the structure, depth, and/or segmentation of the digital images.