Robert Boschgmbh

Carnegie Mellon University

Filipe J Cabrita Condessa

Jeremy Zico Kolter

Wan-Yi Lin

Devin T Willmott

João D Semedo

Jeremy Zieg Kolter

Fatemeh Sheikholeslami

Karren Yang

Yiding Jiang

Manash Pratim

Ruslan Salakhutdinov

Stefan Gehrer

Anit Kumar Sahu

Robin Hutmacher

Po-Wei Wang

Mohammad Sadegh Norouzzadeh

Chen Qiu

Laura Beggel

S Alireza Golestaneh

Marcus Pereira

Ivan Batalov

Jeffrey Thompson

Anh Nguyen

Renan Alfredo Rojas Gomez

Christina Baek

Asher Trockman

Mingjie Sun

Jianghong Shi

Rajshekhar Das

Aditi Raghunathan

Bahare Azari

Hariharan Manikandan

Yutong He

Nhung Thi Phuong Ngo

Methods and systems for training a machine learning model with measurement data captured during a manufacturing process. Measurement data regarding a physical characteristic of a plurality of manufactured parts is received as measured by a plurality of sensors at various manufacturing stations. A time-series dynamics machine learning model encodes the measurement data into a latent space having a plurality of nodes. Each node is associated with the measurement data of one of the manufactured parts and at one of the manufacturing stations. A batch of the measurement data can be built, the batch include a first node and a first plurality of nodes immediately connected to the first node via first edges, and measured in time earlier than the first node. A prediction machine learning model can predict measurements of a first of the manufactured parts based on the latent space of the batch of nodes.

Methods and systems for training a machine learning model with measurement data captured during manufacturing process

A system includes a controller configured to generate an original patch utilizing Bayesian optimization, output the original patch at a display at a scene and determine if the original patch does not meet a success criteria of the machine-learning model, in response to the original patch not meeting the success criteria, upscaling the patch, decompose the upscaled patch into o components, for each of the components, utilize Bayesian optimization to update one of the components of the upscaled patch and freezing the other components to generate an updated patch, in response to the updated patch meeting the success criteria, output the updated upscaled patch, and in response to the updated upscaled patch not meeting the success criteria, iteratively update the unfrozen components and determine if the success criteria is met and if not met, unfreeze the frozen components and iteratively update the unfrozen components until the success criteria is met.

System and method for high-resolution blackbox patch attack with Bayesian optimization

A method discloses receiving, at a cross-attention layer of a model, first text data describing a first object and second text data describing a first scene, wherein the first text data includes a description of a location of the first object, utilizing the model with cross-attention layers, concatenating the first text data and the second text data to generate a prompt; generating, a broadcasted location mask constructed from at least the location; generating, a broadcasted all-one matrix associated with the second text data described the first scene; computing a key matrix and a value matrix utilizing separate linear projections of the prompt; computing a query matrix utilizing linear projections; generating a broadcasted location matrix in response to concatenating the broadcasted location mask and the broadcasted all-one matrix; generating a cross-attention map utilizing the query matrix, the key matrix, and the broadcasted location matrix; and outputting a final image.

System and method for localized text to image generation for free via cross attention

A computer-implemented method includes converting tabular data to a text representation, generating metadata associated with the text representation of the tabular data, outputting one or more natural language data descriptions indicative of the tabular data in response to utilizing a large language model (LLM) and zero-shot prompting of the metadata and text representation of the tabular data, outputting one or more summaries utilizing the LLM and appending a prompt on the one or more natural language data descriptions, selecting a single summary of the one or more summaries in response to the single summary having a smallest validation rate, receiving a query associated with the tabular data, outputting one or more predictions associated with the query, and in response to meeting a convergence threshold with the one or more predictions generated from the one or more iterations, output a final prediction associated with the query.

System and method for utilizing weak learners on large language models

Methods and systems are disclosed for generating training data for a machine learning model for better performance of the model. A source image is selected from an image database, along with a target image. An image segmenter is utilized with the source image to generate a source image segmentation mask having a foreground region and a background region. The same is performed with the target image to generate a target image segmentation mask having a foreground region and a background region. Foregrounds and backgrounds of the source image and target image are determined based on the masks. The target image foreground is removed from the target image, and the source image foreground is inserted into the target image to create an augmented image having the source image foreground and the target image background. The training data for the machine learning model is updated to include this augmented image.

Data augmentation for domain generalization

A computer-implemented method for training a machine learning network includes receiving an input data from one or more sensors, selecting one or more batch samples from the input data, wherein the batch samples include one or more perturbed samples from a source class configured to be misclassified into a target class, identifying the one or more perturbed samples from the one or more batch samples, determining a trigger event in response to identification of a trigger pattern of the one or more batch samples, wherein the trigger pattern induces a pre-determined response on a classifier, outputting a classification in response to identification of the trigger pattern via the classifier, and outputting a set of trigger patterns extracted from the machine-learning network.

Method and system for breaking backdoored classifiers through adversarial examples

Methods and systems of estimating an accuracy of a neural network on out-of-distribution data. In-distribution accuracies of a plurality of machine learning models trained with in-distribution data are determined. The plurality of machine learning models includes a first model, and a remainder of models. In-distribution agreement is determined between (i) an output of the first machine learning model executed with an in-distribution dataset and (ii) outputs of a remainder of the plurality of machine learning models executed with the in-distribution dataset. The machine learning models are also executed with an unlabeled out-of-distribution dataset, and an out-of-distribution agreement is determined. The in-distribution agreement is compared with the out-of-distribution agreement. Based on a result of the comparison being within a threshold, an accuracy of the first machine learning model on the unlabeled out-of-distribution dataset is estimated based on (i) the in-distribution accuracies, (ii) the in-distribution agreement, and (iii) the out-of-distribution agreement.

Performance of neural networks under distribution shift

A computer-implemented method for training a machine learning network. The method may include receiving an input data, selecting one or more batch samples from the input data, applying a perturbation object onto the one or more batch samples to create a perturbed sample, running the perturbed sample through the machine learning network, updating the perturbation object in response to the function in response to running the perturbed sample, and outputting the perturbation object in response to exceeding a convergence threshold.

System and method for utilizing perturbation in a multimodal environment

Performing semantic segmentation in an absence of labels for one or more semantic classes is provided. One or more weak predictors are utilized to obtain label proposals of novel classes for an original dataset for which at least a subset of sematic classes are unlabeled classes. The label proposals are merged with ground truth of the original dataset to generate a merged dataset, the ground truth defining labeled classes of portions of the original dataset. A machine learning model is trained using the merged dataset. The machine learning model is utilized for performing semantic segmentation on image data.

Learning semantic segmentation models in the absence of a portion of class labels

A computer-implemented method for training a machine-learning network, wherein the network includes receiving an input data from a sensor, wherein the input data includes data indicative of an image, wherein the sensor includes a video, radar, LiDAR, sound, sonar, ultrasonic, motion, or thermal imaging sensor, generating an adversarial version of the input data utilizing an optimizer, wherein the adversarial version of the input data utilizes a subset of the input data, parameters associated with the optimizer, and one or more perturbation tiles, determining loss function value in response to the adversarial version of the input data and a classification of the adversarial version of the input data, determining a perturbation tile in response the loss function value associated with one or more subsets of the adversarial version of the input data, and output a perturbation that includes at least the perturbation tile.

Method and system for low-query black-box universal attacks

A convolutional neural network system includes a sensor and a controller, wherein the controller is configured to receive an image from the sensor, divide the image into patches, each patch of size p, extract, via a first convolutional layer, a feature map having a number of channels based on a feature detector of size p, wherein the feature detector has a stride equal to size p, refine the feature map by alternatingly applying depth-wise convolutional layers and point-wise convolutional layers to obtain a refined feature map, wherein the number of channels in the feature map and the size of the feature map remains constant throughout all operations in the refinement; and output the refined feature map.

Image processing via isotonic convolutional neural networks

A multimodal perception system for an autonomous vehicle includes a first sensor that is one of a video, RADAR, LIDAR, or ultrasound sensor, and a controller. The controller may be configured to, receive a first signal from a first sensor, a second signal from a second sensor, and a third signal from a third sensor, extract a first feature vector from the first signal, extract a second feature vector from the second signal, extract a third feature vector from the third signal, determine an odd-one-out vector from the first, second, and third feature vectors via an odd-one-out network of a machine learning network, based on inconsistent modality prediction, fuse the first, second, and third feature vectors and odd-one-out vector into a fused feature vector, output the fused feature vector, and control the autonomous vehicle based on the fused feature vector.

Defending multimodal fusion models against single-source adversaries

Methods and systems are disclosed for quantizing images using machine-learning. A plurality of input images are received from a sensor (e.g., a camera), wherein each input image includes a plurality of pixels. Utilizing an image-to-image machine-learning model, each pixel is assigned a new pixel color. Utilizing a mixer machine-learning model, each new pixel color is converted to one of a fixed number of colors to produce a plurality of quantized images, with each quantized image corresponding to one of the input images. A loss function is determined based on an alignment of each input image with its corresponding quantized image via a pre-trained reference machine-learning model. One or more parameters of the image-to-image machine-learning model and the mixer model are updated based on the loss function. The process repeats, with each iteration updating the parameters of the image-to-image machine-learning model and the mixer model, until convergence, resulting in trained models.

Image quantization using machine learning

A computational method for training a classifier. The method includes receiving a training data set comprised of pairs of training input and output signals, the classifier parameterized by parameters, a class-dependent allowed perturbation for each of at least two different classes and including a first class-dependent allowed perturbation for a first class and a second class-dependent allowed perturbation for a second class, and a loss function. The method further includes partitioning the training data set into a first subset labelled with a first label and a second subset labelled with a second label. The method also includes calculating a first loss in response to the first subset and the first class-dependent allowed perturbation and a second loss calculated in response to the second subset and the second class-dependent allowed perturbation. The method also includes updating the parameters in response to the first and second losses to obtain updated parameters.

Asymmetrical robustness for classification in adversarial environments

A system and method is disclosed for labeling an unlabeled dataset, with a labeling budget constraint and noisy oracles (i.e. noisy labels provided by annotator), using a noisy labeled dataset from another domain or application. The system and method combine active learning with noisy labels and active learning with domain adaptation to enhance classification performance.

Growing community of inventors

Pittsburgh, PA, United States of America

Filipe J Cabrita Condessa