Salesforce, Inc.

Salesforce Com, Inc.

Chetan Ramaiah

Caiming Xiong

Ran Xu

Shu Zhang

Sönke Rohde

Brian J Lonsdorf

David J Woodward

Owen Winne Schoppe

Jessica Lundin

Michael Reynolds Sollami

Alan Martin Ross

Junnan Li

Mingfei Gao

Zeyuan Chen

Peng Tang

Luyu Yang

Embodiments described herein provide an online domain adaptation framework based on cross-domain bootstrapping for online domain adaptation, in which the target domain streaming data is deleted immediately after adapted. At each online query, the data diversity is increased across domains by bootstrapping the source domain to form diverse combinations with the current target query. To fully take advantage of the valuable discrepancies among the diverse combinations, a set of independent learners are trained to preserve the differences. The knowledge of the learners is then integrated by exchanging their predicted pseudo-labels on the current target query to co-supervise the learning on the target domain, but without sharing the weights to maintain the learners' divergence.

Systems and methods for online adaptation for cross-domain streaming data

Embodiments described herein a CROss-Modal Distribution Alignment (CROMDA) model for vision-language pretraining, which can be used for retrieval downstream tasks. In the CROMDA mode, global cross-modal representations are aligned on each unimodality. Specifically, a uni-modal global similarity between an image/text and the image/text feature queue are computed. A softmax-normalized distribution is then generated based on the computed similarity. The distribution thus takes advantage of property of the global structure of the queue. CROMDA then aligns the two distributions and learns a modal invariant global representation. In this way, CROMDA is able to obtain invariant property in each modality, where images with similar text representations should be similar and vice versa.

Systems and methods for vision-language distribution alignment

A method for generating a neural network for detecting one or more objects in images includes generating one or more self-supervised proposal learning losses based on the one or more proposal features and corresponding proposal feature predictions. One or more consistency-based proposal learning losses are generated based on noisy proposal feature predictions and the corresponding proposal predictions without noise. A combined loss is generated using the one or more self-supervised proposal learning losses and one or more consistency-based proposal learning losses. The neural network is updated based on the combined loss.

Proposal learning for semi-supervised object detection

A textual properties model is used to infer values for certain font properties of interest given certain text-related data, such as rendered text images. The model may be used for numerous purposes, such as aiding with document layout, identifying font families that are similar to a given font families, and generating new font families with specific desired properties. In some embodiments, the model is trained from a combination of synthetic data that is labeled with values for the font properties of interest, and partially-labeled data from existing 'real-world' documents.

Machine learning-based inference of granular font properties

The system has a form analysis module that receives an image of a form into which values have been filled for the possible fields of information on the form, such as first name, address, age, and the like. By using a library of form templates, a form analysis module allows both flexibility of form processing and simplicity for the user. That is, the techniques used by the form analysis module allow the processing of any form image for which the library has a form template example. The form image need not precisely match any form template, but rather may be scaled or shifted relative to a corresponding template. Additionally, the user need only provide the form image itself, without providing any additional exemplars, metadata for training, or the like.

Template-based key-value extraction for inferring OCR key values within form images

Growing community of inventors

Palo Alto, CA, United States of America

Chetan Ramaiah