Home /

Research

Showing 679 - 684 / 897

Find it if You Can: End-to-End Adversarial Erasing for Weakly-Supervised Semantic Segmentation


Authors:  ErikStammes, TomF.H.Runia, MichaelHofmann....
Published date-11/09/2020
Tasks:  SemanticSegmentation, Weakly-SupervisedSemanticSegmentation

Abstract: Semantic segmentation is a task that traditionally requires a large dataset of pixel-level ground truth labels, which is time-consuming and expensive to obtain. Recent advancements in the weakly-supervised setting show …

Predicting Landsat Reflectance with Deep Generative Fusion


Authors:  ShahineBouabid, MaximChernetskiy, MaximeRischard....
Published date-11/09/2020
Tasks:  TimeSeries

Abstract: Public satellite missions are commonly bound to a trade-off between spatial and temporal resolution as no single sensor provides fine-grained acquisitions with frequent coverage. This hinders their potential to assist …

Reward Conditioned Neural Movement Primitives for Population Based Variational Policy Optimization


Authors:  M.TuluhanAkbulut, UtkuBozdogan, AhmetTekden....
Published date-11/09/2020
Tasks:  VariationalInference

Abstract: The aim of this paper is to study the reward based policy exploration problem in a supervised learning approach and enable robots to form complex movement trajectories in challenging reward …

Character-level Representations Improve DRS-based Semantic Parsing Even in the Age of BERT


Authors:  RikvanNoord, AntonioToral, JohanBos....
Published date-11/09/2020
Tasks:  LanguageModelling, SemanticParsing

Abstract: We combine character-level and contextual language model representations to improve performance on Discourse Representation Structure parsing. Character representations can easily be added in a sequence-to-sequence model in either one encoder …

VisBERT: Hidden-State Visualizations for Transformers


Authors:  BettyvanAken, BenjaminWinter, AlexanderLöser....
Published date-11/09/2020
Tasks:  QuestionAnswering

Abstract: Explainability and interpretability are two important concepts, the absence of which can and should impede the application of well-performing neural networks to real-world problems. At the same time, they are …

End-to-end Lane Shape Prediction with Transformers


Authors:  RuijinLiu, Zejianyuan, TieLiu....
Published date-11/09/2020
Tasks:  AutonomousVehicles, LaneDetection

Abstract: Lane detection, the process of identifying lane markings as approximated curves, is widely used for lane departure warning and adaptive cruise control in autonomous vehicles. The popular pipeline that solves …

Filter by

Categories

Tags