Adobe, Inc.

Jiuxiang Gu

Rajiv Jain

Vlad Ion Morariu

Tong Sun

Franck Dernoncourt

Handong Zhao

Jason Wen Yong Kuen

Nikolaos Barmpalios

Zhe Lin

Nedim Lipka

Christopher Alan Tensmeyer

Tong Yu

Ani Nenkova

Ruiyi Zhang

Jason Kuen

Puneet Mathur

Curtis Michael Wigington

Varun Manjunatha

Ashutosh Mehra

Quan Hung Tran

Anandhavelu N

Dat Ba Huynh

Yufan Zhou

Shijie Geng

Peizhao Li

Thi Kim Phung Lai

Zhendong Chu

Verena Kaynig-Fittkau

Systems and methods for image processing are described. Embodiments of the present disclosure receive a training image and a caption for the training image, wherein the caption includes text describing an object in the training image; generate a pseudo mask for the object using a teacher network based on the text describing the object; generate a mask for the object using a student network; and update parameters of the student network based on the mask and the pseudo mask.

Open vocabulary instance segmentation

Methods and systems disclosed herein relate generally to systems and methods for generating visual relationship graphs that identify relationships between objects depicted in an image. A vision-language application uses transformer encoders to generate a graph structure, in which the graph structure represents a dependency between a first region and a second region of an image. The dependency indicates that a contextual representation of the first region was derived, at least in part, by processing the second region. The contextual representation identifies a predicted identity of an image object depicted in the first region. The predicted identity is determined at least in part by identifying a relationship between the first region and other data objects associated with various modalities.

Self-supervised visual-relationship probing

In implementations of systems for training language models and preserving privacy, a computing device implements a privacy system to predict a next word after a last word in a sequence of words by processing input data using a machine learning model trained on training data to predict next words after last words in sequences of words. The training data describes a corpus of text associated with clients and including sensitive samples and non-sensitive samples. The machine learning model is trained by sampling a client of the clients and using a subset of the sensitive samples associated with the client and a subset of the non-sensitive samples associated with the client to update parameters of the machine learning model. The privacy system generates an indication of the next word after the last word in the sequence of words for display in a user interface.

Training language models and preserving privacy

This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that train a named entity recognition (NER) model with noisy training data through a self-cleaning discriminator model. For example, the disclosed systems utilize a self-cleaning guided denoising framework to improve NER learning on noisy training data via a guidance training set. In one or more implementations, the disclosed systems utilize, within the denoising framework, an auxiliary discriminator model to correct noise in the noisy training data while training an NER model through the noisy training data. For example, while training the NER model to predict labels from the noisy training data, the disclosed systems utilize a discriminator model to detect noisy NER labels and reweight the noisy NER labels provided for training in the NER model.

Generating an improved named entity recognition model using noisy data with a self-cleaning discriminator model

Systems and methods for performing Document Visual Question Answering tasks are described. A document and query are received. The document encodes document tokens and the query encodes query tokens. The document is segmented into nested document sections, lines, and tokens. A nested structure of tokens is generated based on the segmented document. A feature vector for each token is generated. A graph structure is generated based on the nested structure of tokens. Each graph node corresponds to the query, a document section, a line, or a token. The node connections correspond to the nested structure. Each node is associated with the feature vector for the corresponding object. A graph attention network is employed to generate another embedding for each node. These embeddings are employed to identify a portion of the document that includes a response to the query. An indication of the identified portion of the document is be provided.

Enhanced document visual question answering system via hierarchical attention

The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate a digital document hierarchy comprising layers of parent-child element relationships from the visual elements. For example, for a layer of the layers, the disclosed systems determine, from the visual elements, candidate parent visual elements and child visual elements. In addition, for the layer of the layers, the disclosed systems generate, from the feature embeddings utilizing a neural network, element classifications for the candidate parent visual elements and parent-child element link probabilities for the candidate parent visual elements and the child visual elements. Moreover, for the layer, the disclosed systems select parent visual elements from the candidate parent visual elements based on the parent-child element link probabilities. Further, the disclosed systems utilize the digital document hierarchy to generate an interactive digital document from the digital document image.

Extracting document hierarchy using a multimodal, layer-wise link prediction neural network

The technology described includes methods for pretraining a document encoder model based on multimodal self cross-attention. One method includes receiving image data that encodes a set of pretraining documents. A set of sentences is extracted from the image data. A bounding box for each sentence is generated. For each sentence, a set of predicted features is generated by using an encoder machine-learning model. The encoder model performs cross-attention between a set of masked-textual features for the sentence and a set of masked-visual features for the sentence. The set of masked-textual features is based on a masking function and the sentence. The set of masked-visual features is based on the masking function and the corresponding bounding box. A document-encoder model is pretrained based on the set of predicted features for each sentence and pretraining tasks. The pretraining tasks includes masked sentence modeling, visual contrastive learning, or visual-language alignment.

Unified pretraining framework for document understanding

The present disclosure relates to systems, non-transitory computer-readable media, and methods that implement a neural network framework for interactive multi-round image generation from natural language inputs. Specifically, the disclosed systems provide an intelligent framework (i.e., a text-based interactive image generation model) that facilitates a multi-round image generation and editing workflow that comports with arbitrary input text and synchronous interaction. In particular embodiments, the disclosed systems utilize natural language feedback for conditioning a generative neural network that performs text-to-image generation and text-guided image modification. For example, the disclosed systems utilize a trained model to inject textual features from natural language feedback into a unified joint embedding space for generating text-informed style vectors. In turn, the disclosed systems can generate an image with semantically meaningful features that map to the natural language feedback. Moreover, the disclosed systems can persist these semantically meaningful features throughout a refinement process and across generated images.

Utilizing a generative neural network to interactively create and modify digital images based on natural language feedback

Systems and methods for image processing are described. The systems and methods include receiving a low-resolution image; generating a feature map based on the low-resolution image using an encoder of a student network, wherein the encoder of the student network is trained based on comparing a predicted feature map from the encoder of the student network and a fused feature map from a teacher network, and wherein the fused feature map represents a combination of first feature map from a high-resolution encoder of the teacher network and a second feature map from a low-resolution encoder of the teacher network; and decoding the feature map to obtain prediction information for the low-resolution image.

Multi-scale distillation for low-resolution detection

Systems and methods for document editing are provided. One aspect of the systems and methods includes obtaining a document and a natural language edit request. Another aspect of the systems and methods includes generating a structured edit command using a machine learning model based on the document and the natural language edit request. Yet another aspect of the systems and methods includes generating a modified document based on the document and the structured edit command, where the modified document includes a revision of the document that incorporates the natural language edit request.

Language-guided document editing

One example method involves operations for a processing device that include receiving, by a machine learning model trained to generate a search result, a search query for a text input. The machine learning model is trained by receiving pre-training data that includes multiple documents. Pre-training the machine learning model by generating, using an encoder, feature embeddings for each of the documents included in the pre-training data. The feature embeddings are generated by applying a masking function to visual and textual features in the documents. Training the machine learning model also includes generating, using the feature embeddings, output features for the documents by concatenating the feature embeddings and applying a non-linear mapping to the feature embeddings. Training the machine learning model further includes applying a linear classifier to the output features. Additionally, operations include generating, for display, a search result using the machine learning model based on the input.

Self-supervised document representation learning

Systems, methods, and non-transitory computer-readable media can generate a natural language model that provides user-entity differential privacy. For example, in one or more embodiments, a system samples sensitive data points from a natural language dataset. Using the sampled sensitive data points, the system determines gradient values corresponding to the natural language model. Further, the system generates noise for the natural language model. The system generates parameters for the natural language model using the gradient values and the noise, facilitating simultaneous protection of the users and sensitive entities associated with the natural language dataset. In some implementations, the system generates the natural language model through an iterative process (e.g., by iteratively modifying the parameters).

Growing community of inventors

College Park, MD, United States of America

Jiuxiang Gu