Home /
Research
Showing 271 - 276 / 904
SelfText Beyond Polygon: Unconstrained Text Detection with Box Supervision and Dynamic Self-Training
WeijiaWu, EnzeXie, RuimaoZhang....
Published date-11/26/2020
Although a polygon is a more accurate representation than an upright bounding box for text detection, the annotations of polygons are extremely expensive and challenging. Unlike existing works that employ …
Episodic Self-Imitation Learning with Hindsight
TianhongDai, HengyanLiu, AnilAnthonyBharath....
Published date-11/26/2020
ContinuousControl, ImitationLearning
Episodic self-imitation learning, a novel self-imitation algorithm with a trajectory selection module and an adaptive loss function, is proposed to speed up reinforcement learning. Compared to the original self-imitation learning …
NLPStatTest: A Toolkit for Comparing NLP System Performance
HaotianZhu, DeniseMak, JesseGioannini....
Published date-11/26/2020
Statistical significance testing centered on p-values is commonly used to compare NLP system performance, but p-values alone are insufficient because statistical significance differs from practical significance. The latter can be …
Physics-informed neural networks for myocardial perfusion MRI quantification
RudolfL.M.vanHerten, AmedeoChiribiri, MarcelBreeuwer....
Published date-11/25/2020
Tracer-kinetic models allow for the quantification of kinetic parameters such as blood flow from dynamic contrast-enhanced magnetic resonance (MR) images. Fitting the observed data with multi-compartment exchange models is desirable, …
Ranking Deep Learning Generalization using Label Variation in Latent Geometry Graphs
CarlosLassance, LouisBéthune, MyriamBontonou....
Published date-11/25/2020
Measuring the generalization performance of a Deep Neural Network (DNN) without relying on a validation set is a difficult task. In this work, we propose exploiting Latent Geometry Graphs (LGGs) …
No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems
NimitS.Sohoni, JaredA.Dunnmon, GeoffreyAngus....
Published date-11/25/2020
Clustering, ImageClassification
In real-world classification tasks, each class often comprises multiple finer-grained "subclasses." As the subclass labels are frequently unavailable, models trained using only the coarser-grained class labels often exhibit highly variable …