Home /

Research

Showing 727 - 732 / 897

Learning a Geometric Representation for Data-Efficient Depth Estimation via Gradient Field and Contrastive Loss


Authors:  DongseokShim, H.JinKim....
Published date-11/06/2020
Tasks:  DepthEstimation, MonocularDepthEstimation, ObjectDetection, Self-SupervisedLearning

Abstract: Estimating a depth map from a single RGB image has been investigated widely for localization, mapping, and 3-dimensional object detection. Recent studies on a single-view depth estimation are mostly based …

Feature Removal Is a Unifying Principle for Model Explanation Methods


Authors:  IanCovert, ScottLundberg, Su-InLee....
Published date-11/06/2020

Abstract: Researchers have proposed a wide variety of model explanation approaches, but it remains unclear how most methods are related or when one method is preferable to another. We examine the …

Trust Issues: Uncertainty Estimation Does Not Enable Reliable OOD Detection On Medical Tabular Data


Authors:  DennisUlmer, LottaMeijerink, GiovanniCinà....
Published date-11/06/2020

Abstract: When deploying machine learning models in high-stakes real-world environments such as health care, it is crucial to accurately assess the uncertainty concerning a model's prediction on abnormal inputs. However, there …

Deep Transfer Learning for Automated Diagnosis of Skin Lesions from Photographs


Authors:  EmmaRocheteau, DoyoonKim....
Published date-11/06/2020
Tasks:  TransferLearning

Abstract: Melanoma is not the most common form of skin cancer, but it is the most deadly. Currently, the disease is diagnosed by expert dermatologists, which is costly and requires timely …

From Dataset Recycling to Multi-Property Extraction and Beyond


Authors:  TomaszDwojak, MichałPietruszka, ŁukaszBorchmann....
Published date-11/06/2020
Tasks:  MachineReadingComprehension, ReadingComprehension

Abstract: This paper investigates various Transformer architectures on the WikiReading Information Extraction and Machine Reading Comprehension dataset. The proposed dual-source model outperforms the current state-of-the-art by a large margin. Next, we …

User-Dependent Neural Sequence Models for Continuous-Time Event Data


Authors:  AlexBoyd, RobertBamler, StephanMandt....
Published date-11/06/2020
Tasks:  VariationalInference

Abstract: Continuous-time event data are common in applications such as individual behavior data, financial transactions, and medical health records. Modeling such data can be very challenging, in particular for applications with …

Filter by

Categories

Tags