Samsung Electronics Co., Ltd.

Yilin Shen

Hongxia Jin

Avik Ray

Yue Deng

Burak Uzkent

Yu Wang

Yen-Chang Hsu

Xiangyu Zeng

Vasili Ramanishka

Pengfei Hu

Rui Chen

Tong Yu

Peixi Xiong

Chou-Chang Yang

Ching-Hua Lee

Rakshith Sharma Srinivasa

Yashas Malur Saidutta

Shangqian Gao

Changsheng Zhao

Ting Hua

Fenjiao Wang

Qian Lou

An apparatus for performing image processing, may include at least one processor configured to: input an image to a vision transformer comprising a plurality of encoders that correspond to at least one fixed encoder and a plurality of adaptive encoders; process the image via the at least one fixed encoder to obtain image representations; determine one or more layers of the plurality of adaptive encoders to drop, by inputting the image representations to a policy network configured to determine layer dropout actions for the plurality of adaptive encoders; and obtain a class of the input image using remaining layers of the plurality of adaptive encoders other than the dropped one or more layers.

Method and apparatus for classifying images using an artificial intelligence model

A method of performing a multimodal tasks by using a multimodal model that includes a text encoder and a vision encoder, may include obtaining a text feature from the query via the text encoder; obtaining an image feature from the one or more input images via the vision encoder; and outputting a response to the query based on similarity between the text feature and the image feature, wherein weights vectors of the text encoder and the vision encoder are pruned and shared according to a sharing vector and a pruning vector that are generated by a hypernetwork, and wherein the hypernetwork and the multimodal model are jointly trained to minimize at least one of a difference between the weight vectors in the text encoder and the vision encoder, a difference between the weight vectors in different layers of the text encoder, and a number of parameters in the multimodal model.

Apparatus and method for sharing and pruning weights for vision and language models

A method includes obtaining, using a first electronic device, a weight matrix associated with a trained transformer model. The method also includes factorizing the weight matrix into a dictionary weight matrix and an intermediate matrix. The method further includes pruning the intermediate matrix to generate a sparse intermediate matrix. The method also includes fine-tuning the sparse intermediate matrix based on a training dataset to generate a fine-tuned sparse intermediate matrix. The method further includes determining an index matrix and a coefficient matrix based on the fine-tuned sparse intermediate matrix. In addition, the method includes deploying the dictionary weight matrix, the index matrix, and the coefficient matrix to a second electronic device without deploying the weight matrix to the second electronic device. A number of parameters in the dictionary weight matrix, the index matrix, and the coefficient matrix is smaller than a number of parameters in the weight matrix.

Small and fast transformer model for multi-modal or other tasks

A method of training a neural network model includes generating a positive image based on an original image, generating a positive text corresponding to the positive image based on an original text corresponding to the original image, the positive text referring to an object in the positive image, constructing a positive image-text pair for the object based on the positive image and the positive text, constructing a negative image-text pair for the object based on the original image and a negative text, the negative text not referring to the object, training the neural network model based on the positive image-text pair and the negative image-text pair to output features representing an input image-text pair, and identifying the object in the original image based on the features representing the input image-text pair.

Supervised contrastive learning for visual grounding

A method includes obtaining, using at least one processing device, noisy speech signals and extracting, using the at least one processing device, acoustic features from the noisy speech signals. The method also includes receiving, using the at least one processing device, a predicted speech mask from a speech mask prediction model based on a first acoustic feature subset and receiving, using the at least one processing device, a predicted noise mask from a noise mask prediction model based on a second acoustic feature subset. The method further includes providing, using the at least one processing device, predicted speech features determined using the predicted speech mask and predicted noise features determined using the predicted noise mask to a filtering mask prediction model. In addition, the method includes generating, using the at least one processing device, a clean speech signal using a predicted filtering mask output by the filtering mask prediction model.

Speech denoising networks using speech and noise modeling

A method includes identifying multiple tokens contained in an input utterance. The method also includes generating slot labels for at least some of the tokens contained in the input utterance using a trained machine learning model. The method further includes determining at least one action to be performed in response to the input utterance based on at least one of the slot labels. The trained machine learning model is trained to use attention distributions generated such that (i) the attention distributions associated with tokens having dissimilar slot labels are forced to be different and (ii) the attention distribution associated with each token is forced to not focus primarily on that token itself.

Apparatus and method for compositional spoken language understanding

In one embodiment, a method includes accessing an image and a natural-language question regarding the image and extracting, from the image, a first set of image features at a first level of granularity and a second set of image features at a second level of granularity. The method further includes extracting, from the question, a first set of text features at the first level of granularity and a second set of text features at the second level of granularity; generating a first output representing an alignment between the first set of image features and the first set of text features; generating a second output representing an alignment between the second set of image features and the second set of text features; and determining an answer to the question based on the first output and the second output.

Multi-granularity alignment for visual question answering

A method includes obtaining a batch of training data including multiple paired image-text pairs and multiple unpaired image-text pairs, where each paired image-text pair and each unpaired image-text pair includes an image and a text. The method also includes training a machine learning model using the training data based on an optimization of a combination of losses. The losses include, for each paired image-text pair, (i) a first multi-modal representation loss based on the paired image-text pair and (ii) a second multi-modal representation loss based on two or more unpaired image-text pairs, selected from among the multiple unpaired image-text pairs, wherein each of the two or more unpaired image-text pairs includes either the image or the text of the paired image-text pair.

System and method for supervised contrastive learning for multi-modal tasks

A method includes obtaining, using at least one processor of an electronic device, an image-query understanding model. The method also includes obtaining, using the at least one processor, an image and a user query associated with the image, where the image includes a target image area and the user query includes a target phrase. The method further includes retraining, using the at least one processor, the image-query understanding model using a correlation between the target image area and the target phrase to obtain a retrained image-query understanding model.

System and method for robust image-query understanding based on contextual features

An electronic device for complex task machine learning includes at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to receive an unknown command for performing a task and generate a prompt regarding the unknown command. The at least one processor is also configured to receive one or more instructions in response to the prompt, where each of the one or more instructions provides information on performing at least a portion of the task. The at least one processor is further configured to determine at least one action for each one of the one or more instructions. In addition, the at least one processor is configured to create a complex action for performing the task based on the at least one action for each one of the one or more instructions.

System and method for complex task machine learning

An apparatus for detecting unsupported utterances in natural language understanding, includes a memory storing instructions, and at least one processor configured to execute the instructions to classify a feature that is extracted from an input utterance of a user, as one of in-domain and out-of-domain (OOD) for a response to the input utterance, obtain an OOD score of the extracted feature, and identify whether the feature is classified as OOD. The at least one processor is further configured to executed the instructions to, based on the feature being identified to be classified as in-domain, identify whether the obtained OOD score is greater than a predefined threshold, and based on the OOD score being identified to be greater than the predefined threshold, re-classify the feature as OOD.

Method and system for detecting unsupported utterances in natural language understanding

An electronic device including a deep memory model includes at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to receive input data to the deep memory model. The at least one processor is also configured to extract a history state of an external memory coupled to the deep memory model based on the input data. The at least one processor is further configured to update the history state of the external memory based on the input data. In addition, the at least one processor is configured to output a prediction based on the extracted history state of the external memory.

System and method for deep memory network

A method includes applying, by at least one processor, a natural language understanding (NLU) model to an input utterance in order to obtain initial slot probability distributions. The method also includes performing, by the at least one processor, a confidence calibration by applying a calibration probability distribution to the initial slot probability distributions in order to generate calibrated slot probability distributions. The calibration probability distribution has a higher number of dimensions than the initial slot probability distributions. The method further includes identifying, by the at least one processor, uncertainties associated with words in the input utterance based on the calibrated slot probability distributions. In addition, the method includes identifying, by the at least one processor, a new concept contained in the input utterance that is not recognized by the NLU model based on the identified uncertainties.

System and method for learning new concepts from input utterances

A recommendation method includes retrieving content consumption data including content consumed and content not consumed. Based on the content consumption data, identifying a first piece of content not consumed. A first feature of the first piece of content related to negative consumption of the first piece of content is determined. A first system is used to revise the first feature to a second feature. A second piece of content including the second feature is provided to an electronic device. The second piece of content is a revised instance of the first piece of content.

Adversarial method and system for generating user preferred contents

A recognition method includes retrieving an input including data of a first window size. The method further includes classifying the input based on comparison of warping distance of the input with a pruning threshold.

Growing community of inventors

Sunnyvale, CA, United States of America

Yilin Shen