Home /

Research

Showing 451 - 456 / 897

Towards Meta-Algorithm Selection

Authors:  AlexanderTornede, MarcelWever, EykeHüllermeier....
Published date-11/17/2020

Abstract: Instance-specific algorithm selection (AS) deals with the automatic selection of an algorithm from a fixed set of candidates most suitable for a specific instance of an algorithmic problem class, where …
Paper Code

Minimal Solvers for Single-View Lens-Distorted Camera Auto-Calibration

Authors:  YaroslavaLochman, OlesDobosevych, RostyslavHryniv....
Published date-11/17/2020
Tasks:  CameraAuto-Calibration, Rectification, SceneLabeling, SceneParsing

Abstract: This paper proposes minimal solvers that use combinations of imaged translational symmetries and parallel scene lines to jointly estimate lens undistortion with either affine rectification or focal length and absolute …
Paper Code

PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization

Authors:  ThomasDefard, AleksandrSetkov, AngeliqueLoesch....
Published date-11/17/2020
1x1 Convolution
Activation Functions
Average Pooling
Batch Normalization
Bottleneck Residual Block
Tasks:  AnomalyDetection, UnsupervisedAnomalyDetection

Abstract: We present a new framework for Patch Distribution Modeling, PaDiM, to concurrently detect and localize anomalies in images in a one-class learning setting. PaDiM makes use of a pretrained convolutional …
Paper Code

A User's Guide to Calibrating Robotics Simulators

Authors:  BhairavMehta, AnkurHanda, DieterFox....
Published date-11/17/2020
Tasks:  DecisionMaking

Abstract: Simulators are a critical component of modern robotics research. Strategies for both perception and decision making can be studied in simulation first before deployed to real world systems, saving on …
Paper Code

Recursive Inference for Variational Autoencoders

Authors:  MinyoungKim, VladimirPavlovic....
Published date-11/17/2020
Tasks:  VariationalInference

Abstract: Inference networks of traditional Variational Autoencoders (VAEs) are typically amortized, resulting in relatively inaccurate posterior approximation compared to instance-wise variational optimization. Recent semi-amortized approaches were proposed to address this drawback; …
Paper Code

Combining Reinforcement Learning with Model Predictive Control for On-Ramp Merging

Authors:  JosephLubars, HarshGupta, AdnanRaja....
Published date-11/17/2020
Tasks:  AutonomousDriving, MotionPlanning

Abstract: We consider the problem of designing an algorithm to allow a car to autonomously merge on to a highway from an on-ramp. Two broad classes of techniques have been proposed …
Paper Code

Filter by

Categories

Tags