b'Amazon'

research

∙ 05/03/2021

Synthetic Data for Model Selection

Recent improvements in synthetic data generation make it possible to pro...

Matan Fintz, et al. ∙

research

∙ 05/06/2022

Federated Learning with Noisy User Feedback

Machine Learning (ML) systems are getting increasingly popular, and driv...

Rahul Sharma, et al. ∙

research

∙ 05/05/2019

P3O: Policy-on Policy-off Policy Optimization

On-policy reinforcement learning (RL) algorithms have high sample comple...

Rasool Fakoor, et al. ∙

research

∙ 02/13/2020

Continual Universal Object Detection

Object detection has improved significantly in recent years on multiple ...

Xialei Liu, et al. ∙

research

∙ 06/09/2020

Fair Bayesian Optimization

Given the increasing importance of machine learning (ML) in our lives, a...

Valerio Perrone, et al. ∙

research

∙ 09/07/2021

Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloud

Understanding the predictions made by machine learning (ML) models and t...

Michaela Hardt, et al. ∙

research

∙ 08/20/2019

Action recognition with spatial-temporal discriminative filter banks

Action recognition has seen a dramatic performance improvement in the la...

Brais Martinez, et al. ∙

research

∙ 11/13/2019

SAVEHR: Self Attention Vector Representations for EHR based Personalized Chronic Disease Onset Prediction and Interpretability

Chronic disease progression is emerging as an important area of investme...

Sunil Mallya, et al. ∙

research

∙ 07/07/2021

Predicting with Confidence on Unseen Distributions

Recent work has shown that the performance of machine learning models ca...

Devin Guillory, et al. ∙

research

∙ 02/03/2022

DocBed: A Multi-Stage OCR Solution for Documents with Complex Layouts

Digitization of newspapers is of interest for many reasons including pre...

Wenzhen Zhu, et al. ∙

research

∙ 03/20/2019

OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations

We present a novel model called OCGAN for the classical problem of one-c...

Pramuditha Perera, et al. ∙

research

∙ 05/20/2021

More Than Just Attention: Learning Cross-Modal Attentions with Contrastive Constraints

Attention mechanisms have been widely applied to cross-modal tasks such ...

Yuxiao Chen, et al. ∙

research

∙ 01/10/2019

Region Proposal by Guided Anchoring

Region anchors are the cornerstone of modern object detection techniques...

Jiaqi Wang, et al. ∙

research

∙ 11/12/2019

Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Neural Networks

We explore the problem of selectively forgetting a particular set of dat...

Aditya Golatkar, et al. ∙

research

∙ 06/22/2020

MultiImport: Inferring Node Importance in a Knowledge Graph from Multiple Input Signals

Given multiple input signals, how can we infer node importance in a know...

Namyong Park, et al. ∙

research

∙ 10/29/2021

Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction

Learning on graphs has attracted significant attention in the learning c...

Eli Chien, et al. ∙

research

∙ 07/07/2021

Long Short-Term Transformer for Online Action Detection

In this paper, we present Long Short-term TRansformer (LSTR), a new temp...

Mingze Xu, et al. ∙

research

∙ 02/18/2022

Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network

Heterogeneous Graph Neural Network (HGNN) has been successfully employed...

Tianyu Zhao, et al. ∙

research

∙ 03/22/2022

Mixed Differential Privacy in Computer Vision

We introduce AdaMix, an adaptive differentially private algorithm for tr...

Aditya Golatkar, et al. ∙

research

∙ 01/17/2019

Scale-Aware Attention Network for Crowd Counting

In crowd counting datasets, people appear at different scales, depending...

Rahul Rama Varior, et al. ∙

research

∙ 02/11/2020

Incremental Learning for Metric-Based Meta-Learners

Majority of the modern meta-learning methods for few-shot classification...

Qing Liu, et al. ∙

research

∙ 03/03/2020

Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications

Trained on large datasets, deep learning (DL) can accurately classify vi...

Biagio Brattoli, et al. ∙

research

∙ 05/16/2020

Towards classification parity across cohorts

Recently, there has been a lot of interest in ensuring algorithmic fairn...

Aarsh Patel, et al. ∙

research

∙ 04/07/2022

Class-Incremental Learning with Strong Pre-trained Models

Class-incremental learning (CIL) has been widely studied under the setti...

Tz-Ying Wu, et al. ∙

research

∙ 11/19/2018

Scalable Logo Recognition using Proxies

Logo recognition is the task of identifying and classifying logos. Logo ...

Istvan Fehervari, et al. ∙

research

∙ 04/20/2019

Language Models with Transformers

The Transformer architecture is superior to RNN-based models in computat...

Chenguang Wang, et al. ∙

research

∙ 12/02/2019

A Human-AI Loop Approach for Joint Keyword Discovery and Expectation Estimation in Micropost Event Detection

Microblogging platforms such as Twitter are increasingly being used in e...

Akansha Bhardwaj, et al. ∙

research

∙ 04/13/2020

From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap

Dialogue state tracking (DST) is at the heart of task-oriented dialogue ...

Shuyang Gao, et al. ∙

research

∙ 12/24/2020

Mixed-Privacy Forgetting in Deep Networks

We show that the influence of a subset of the training samples can be re...

Aditya Golatkar, et al. ∙

research

∙ 12/19/2019

TextTubes for Detecting Curved Text in the Wild

We present a detector for curved text in natural images. We model scene ...

Joël Seytre, et al. ∙

research

∙ 01/24/2020

MT-BioNER: Multi-task Learning for Biomedical Named Entity Recognition using Deep Bidirectional Transformers

Conversational agents such as Cortana, Alexa and Siri are continuously w...

Muhammad Raza Khan, et al. ∙

research

∙ 08/06/2020

Interpretable Multi-Step Reasoning with Knowledge Extraction on Complex Healthcare Question Answering

Healthcare question answering assistance aims to provide customer health...

Ye Liu, et al. ∙

research

∙ 05/18/2022

Debiasing Neural Retrieval via In-batch Balancing Regularization

People frequently interact with information retrieval (IR) systems, howe...

Yuantong Li, et al. ∙

research

∙ 08/17/2018

Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation

Direct prediction of 3D body pose and shape remains a challenge even for...

Mohamed Omran, et al. ∙

research

∙ 03/19/2019

Differentially Private Consensus-Based Distributed Optimization

Data privacy is an important concern in learning, when datasets contain ...

Mehrdad Showkatbakhsh, et al. ∙

research

∙ 09/02/2019

FACSIMILE: Fast and Accurate Scans From an Image in Less Than a Second

Current methods for body shape estimation either lack detail or require ...

David Smith, et al. ∙

research

∙ 04/06/2020

SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction

Open relation extraction is the task of extracting open-domain relation ...

Xuming Hu, et al. ∙

research

∙ 12/21/2020

Unifying Homophily and Heterophily Network Transformation via Motifs

Higher-order proximity (HOP) is fundamental for most network embedding m...

Yan Ge, et al. ∙

research

∙ 07/02/2021

Backward-Compatible Prediction Updates: A Probabilistic Approach

When machine learning systems meet real world applications, accuracy is ...

Frederik Träuble, et al. ∙

research

∙ 06/16/2021

End-to-End Spoken Language Understanding for Generalized Voice Assistants

End-to-end (E2E) spoken language understanding (SLU) systems predict utt...

Michael Saxon, et al. ∙

research

∙ 09/14/2021

Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction

Low-resource Relation Extraction (LRE) aims to extract relation facts fr...

Xuming Hu, et al. ∙

research

∙ 09/11/2019

Recognizing Variables from their Data via Deep Embeddings of Distributions

A key obstacle in automated analytics and meta-learning is the inability...

Jonas Mueller, et al. ∙

research

∙ 08/04/2020

Can Adversarial Weight Perturbations Inject Neural Backdoors?

Adversarial machine learning has exposed several security hazards of neu...

Siddhant Garg, et al. ∙

research

∙ 01/15/2019

Imitation-Regularized Offline Learning

We study the problem of offline learning in automated decision systems u...

Yifei Ma, et al. ∙

research

∙ 04/26/2019

Dynamic Mini-batch SGD for Elastic Distributed Training: Learning in the Limbo of Resources

With an increasing demand for training powers for deep learning algorith...

Haibin Lin, et al. ∙

research

∙ 04/28/2020

A Linear Bandit for Seasonal Environments

Contextual bandit algorithms are extremely popular and widely used in re...

Giuseppe Di Benedetto, et al. ∙

research

∙ 06/05/2020

Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access

Most prior work on task-oriented dialogue systems are restricted to a li...

Seokhwan Kim, et al. ∙

research

∙ 02/04/2021

SelfNorm and CrossNorm for Out-of-Distribution Robustness

Normalization techniques are crucial in stabilizing and accelerating the...

Zhiqiang Tang, et al. ∙

research

∙ 11/10/2021

Amazon SageMaker Model Parallelism: A General and Flexible Framework for Large Model Training

With deep learning models rapidly growing in size, systems-level solutio...

Can Karakus, et al. ∙

research

∙ 01/22/2022

Visual Representation Learning with Self-Supervised Attention for Low-Label High-data Regime

Self-supervision has shown outstanding results for natural language proc...

Prarthana Bhattacharyya, et al. ∙

Amazon

Featured Researchers