Filters








33 Hits in 0.48 sec

Drive2Vec: Multiscale State-Space Embedding of Vehicular Sensor Data [article]

David Hallac, Suvrat Bhooshan, Michael Chen, Kacem Abida, Rok Sosic, Jure Leskovec
2018 arXiv   pre-print
With automobiles becoming increasingly reliant on sensors to perform various driving tasks, it is important to encode the relevant CAN bus sensor data in a way that captures the general state of the vehicle in a compact form. In this paper, we develop a deep learning-based method, called Drive2Vec, for embedding such sensor data in a low-dimensional yet actionable form. Our method is based on stacked gated recurrent units (GRUs). It accepts a short interval of automobile sensor data as input
more » ... computes a low-dimensional representation of that data, which can then be used to accurately solve a range of tasks. With this representation, we (1) predict the exact values of the sensors in the short term (up to three seconds in the future), (2) forecast the long-term average values of these same sensors, (3) infer additional contextual information that is not encoded in the data, including the identity of the driver behind the wheel, and (4) build a knowledge base that can be used to auto-label data and identify risky states. We evaluate our approach on a dataset collected by Audi, which equipped a fleet of test vehicles with data loggers to store all sensor readings on 2,098 hours of driving on real roads. We show in several experiments that our method outperforms other baselines by up to 90%, and we further demonstrate how these embeddings of sensor data can be used to solve a variety of real-world automotive applications.
arXiv:1806.04795v1 fatcat:wpym2uoubbfubkb43r4kfqwq7y

Supervised Multimodal Bitransformers for Classifying Images and Text [article]

Douwe Kiela, Suvrat Bhooshan, Hamed Firooz, Ethan Perez, Davide Testuggine
2020 arXiv   pre-print
Self-supervised bidirectional transformer models such as BERT have led to dramatic improvements in a wide variety of textual classification tasks. The modern digital world is increasingly multimodal, however, and textual information is often accompanied by other modalities such as images. We introduce a supervised multimodal bitransformer model that fuses information from text and image encoders, and obtain state-of-the-art performance on various multimodal classification benchmark tasks,
more » ... forming strong baselines, including on hard test sets specifically designed to measure multimodal performance.
arXiv:1909.02950v2 fatcat:ujdciqsh5faq3jh2yd4lopraae

Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition [article]

Paloma Jeretic, Alex Warstadt, Suvrat Bhooshan, Adina Williams
2020 arXiv   pre-print
Natural language inference (NLI) is an increasingly important task for natural language understanding, which requires one to infer whether a sentence entails another. However, the ability of NLI models to make pragmatic inferences remains understudied. We create an IMPlicature and PRESupposition diagnostic dataset (IMPPRES), consisting of >25k semiautomatically generated sentence pairs illustrating well-studied pragmatic inference types. We use IMPPRES to evaluate whether BERT, InferSent, and
more » ... W NLI models trained on MultiNLI (Williams et al., 2018) learn to make pragmatic inferences. Although MultiNLI appears to contain very few pairs illustrating these inference types, we find that BERT learns to draw pragmatic inferences. It reliably treats scalar implicatures triggered by "some" as entailments. For some presupposition triggers like "only", BERT reliably recognizes the presupposition as an entailment, even when the trigger is embedded under an entailment canceling operator like negation. BOW and InferSent show weaker evidence of pragmatic reasoning. We conclude that NLI training encourages models to learn some, but not all, pragmatic inferences.
arXiv:2004.03066v2 fatcat:qbxcklmyb5dchat7bnq43oayla

Needles in Haystacks: On Classifying Tiny Objects in Large Images [article]

Nick Pawlowski, Suvrat Bhooshan, Nicolas Ballas, Francesco Ciompi, Ben Glocker, Michal Drozdzal
2020 arXiv   pre-print
In some important computer vision domains, such as medical or hyperspectral imaging, we care about the classification of tiny objects in large images. However, most Convolutional Neural Networks (CNNs) for image classification were developed using biased datasets that contain large objects, in mostly central image positions. To assess whether classical CNN architectures work well for tiny object classification we build a comprehensive testbed containing two datasets: one derived from MNIST
more » ... s and one from histopathology images. This testbed allows controlled experiments to stress-test CNN architectures with a broad spectrum of signal-to-noise ratios. Our observations indicate that: (1) There exists a limit to signal-to-noise below which CNNs fail to generalize and that this limit is affected by dataset size - more data leading to better performances; however, the amount of training data required for the model to generalize scales rapidly with the inverse of the object-to-image ratio (2) in general, higher capacity models exhibit better generalization; (3) when knowing the approximate object sizes, adapting receptive field is beneficial; and (4) for very small signal-to-noise ratio the choice of global pooling operation affects optimization, whereas for relatively large signal-to-noise values, all tested global pooling operations exhibit similar performance.
arXiv:1908.06037v2 fatcat:b5r2qs7cafhhhpnfdmk77pieaa

ShortFuse: Biomedical Time Series Representations in the Presence of Structured Information [article]

Madalina Fiterau, Suvrat Bhooshan, Jason Fries, Charles Bournhonesque, Jennifer Hicks, Eni Halilaj, Christopher Ré, Scott Delp
2017 arXiv   pre-print
3-13 Number of layers all CNN models 1-10 Resolutions Multiresolution CNN 256 -128 -64 -32 -16 Kernel Multiple Kernel Learning RBF Number of trees Random Forests 10 -1000 Fiterau, Bhooshan  ... 
arXiv:1705.04790v2 fatcat:2sth3jnd4rawhj3acmoy3jazqq

ShortFuse: Biomedical Time Series Representations in the Presence of Structured Information

Madalina Fiterau, Suvrat Bhooshan, Jason Fries, Charles Bournhonesque, Jennifer Hicks, Eni Halilaj, Christopher Ré, Scott Delp
2017
In healthcare applications, temporal variables that encode movement, health status and longitudinal patient evolution are often accompanied by rich structured information such as demographics, diagnostics and medical exam data. However, current methods do not jointly optimize over structured covariates and time series in the feature extraction process. We present ShortFuse, a method that boosts the accuracy of deep learning models for time series by explicitly modeling temporal interactions and
more » ... dependencies with structured covariates. ShortFuse introduces hybrid convolutional and LSTM cells that incorporate the covariates via weights that are shared across the temporal domain. ShortFuse outperforms competing models by 3% on two biomedical applications, forecasting osteoarthritis-related cartilage degeneration and predicting surgical outcomes for cerebral palsy patients, matching or exceeding the accuracy of models that use features engineered by domain experts.
pmid:30882086 pmcid:PMC6417829 fatcat:7sz2rianvjbqzl2vnvxmffeguu

Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition

Paloma Jeretic, Alex Warstadt, Suvrat Bhooshan, Adina Williams
2020 Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics   unpublished
Natural language inference (NLI) is an increasingly important task for natural language understanding, which requires one to infer whether a sentence entails another. However, the ability of NLI models to make pragmatic inferences remains understudied. We create an IMPlicature and PRESupposition diagnostic dataset (IMPPRES), consisting of >25k semiautomatically generated sentence pairs illustrating well-studied pragmatic inference types. We use IMPPRES to evaluate whether BERT, InferSent, and
more » ... W NLI models trained on MultiNLI (Williams et al., 2018) learn to make pragmatic inferences. Although MultiNLI appears to contain very few pairs illustrating these inference types, we find that BERT learns to draw pragmatic inferences. It reliably treats scalar implicatures triggered by "some" as entailments. For some presupposition triggers like only, BERT reliably recognizes the presupposition as an entailment, even when the trigger is embedded under an entailment canceling operator like negation. BOW and InferSent show weaker evidence of pragmatic reasoning. We conclude that NLI training encourages models to learn some, but not all, pragmatic inferences.
doi:10.18653/v1/2020.acl-main.768 fatcat:ytu7vlgsn5cjtndgrw7kpqet54

Offset Sampling Improves Deep Learning based Accelerated MRI Reconstructions by Exploiting Symmetry [article]

Aaron Defazio
2020 arXiv   pre-print
Acknowledgements This work was made possible through close collaboration with the fastMRI team at Facebook AI research, including Nafissa Yakubova, Anuroop Sriram, Jure Zbontar, Larry Zitnick, Mark Tygert, Suvrat  ...  Bhooshan and Tullie Murrell, 6 and our collaborators at NYU Langone Health on the fastMRI project [Zbontar et al., 2018] , with special thanks to Florian Knoll, Matthew Muckley, Daniel Sodickson and  ... 
arXiv:1912.01101v2 fatcat:gis5y7vv5jdrnoucmloi6sogcu

MRI Banding Removal via Adversarial Training [article]

Aaron Defazio and Tullie Murrell and Michael P. Recht
2020 arXiv   pre-print
Bhooshan, and our fastMRI project members at NYU Langone Health [22] , with special thanks to Florian Knoll, Matthew Muckley and Daniel Sodickson.  ...  Acknowledgements This work was made possible through close collaboration with the fastMRI team at Facebook AI research, including Nafissa Yakubova, Anuroop Sriram, Jure Zbontar, Larry Zitnick, Mark Tygert and Suvrat  ... 
arXiv:2001.08699v3 fatcat:yfwig26cinbcjjausiqsjoz7t4

Interpretable and Interactive Deep Multiple Instance Learning for Dental Caries Classification in Bitewing X-rays [article]

Benjamin Bergner, Csaba Rohrer, Aiham Taleb, Martha Duchrau, Guilherme De Leon, Jonas Almeida Rodrigues, Falk Schwendicke, Joachim Krois, Christoph Lippert
2021 arXiv   pre-print
Nick Pawlowski, Suvrat Bhooshan, Nicolas Ballas, Francesco Ciompi, Ben Glocker, and Michal Drozdzal. Needles in haystacks: On classifying tiny objects in large images, 2020.  ... 
arXiv:2112.09694v1 fatcat:gr7mqql2pfarneljgae5ausmwu

Adversarial Evaluation of Multimodal Models under Realistic Gray Box Assumption [article]

Ivan Evtimov, Russel Howes, Brian Dolhansky, Hamed Firooz, Cristian Canton Ferrer
2021 arXiv   pre-print
Online; accessed 29 October 2020. 1 [18] Douwe Kiela, Suvrat Bhooshan, Hamed Firooz, and Davide Testuggine.  ... 
arXiv:2011.12902v3 fatcat:y3mpjxkmoba5tng5ufjqm3z5by

Sometimes We Want Translationese [article]

Prasanna Parthasarathi, Koustuv Sinha, Joelle Pineau, Adina Williams
2021 arXiv   pre-print
Paloma Jeretic, Alex Warstadt, Suvrat Bhooshan, and Adina Williams. 2020. Are natural language infer- ence models IMPPRESsive? Learning IMPlicature and PRESupposition.  ... 
arXiv:2104.07623v1 fatcat:fnqmtxkixzahfceedmstw2suxy

The Curse of Performance Instability in Analysis Datasets: Consequences, Source, and Suggestions [article]

Xiang Zhou, Yixin Nie, Hao Tan, Mohit Bansal
2020 arXiv   pre-print
Paloma Jeretic, Alex Warstadt, Suvrat Bhooshan, and Adina Williams. 2020. Are natural language inference models IMPPRESsive? Learning IMPlicature and PRESupposition.  ... 
arXiv:2004.13606v2 fatcat:ruua6cuz7rgfnk2mflgxf27n2m

A Multimodal Framework for the Detection of Hateful Memes [article]

Phillip Lippe, Nithin Holla, Shantanu Chandra, Santhosh Rajamanickam, Georgios Antoniou, Ekaterina Shutova, Helen Yannakoudakis
2020 arXiv   pre-print
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). [14] Douwe Kiela, Suvrat Bhooshan, Hamed Firooz, and Davide Testuggine. 2019.  ... 
arXiv:2012.12871v2 fatcat:rttlifokijczthrcgduaerswey

MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets [article]

Shraman Pramanick, Shivam Sharma, Dimitar Dimitrov, Md Shad Akhtar, Preslav Nakov, Tanmoy Chakraborty
2021 arXiv   pre-print
Douwe Kiela, Suvrat Bhooshan, Hamed Firooz, Ethan Perez, and Davide Testuggine. 2019. Supervised multimodal bitransformers for classifying images and text.  ... 
arXiv:2109.05184v2 fatcat:ntmq4pv6kjdhvebjyohuikqppe
« Previous Showing results 1 — 15 out of 33 results