Home /

Research

Showing 397 - 402 / 897

Exploring Simple Siamese Representation Learning


Authors:  XinleiChen, KaimingHe....
Published date-11/20/2020
Tasks:  RepresentationLearning, UnsupervisedRepresentationLearning

Abstract: Siamese networks have become a common structure in various recent models for unsupervised visual representation learning. These models maximize the similarity between two augmentations of one image, subject to certain …

A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving


Authors:  DiFeng, AliHarakeh, StevenWaslander....
Published date-11/20/2020
Tasks:  AutonomousDriving, ObjectDetection

Abstract: Capturing uncertainty in object detection is indispensable for safe autonomous driving. In recent years, deep learning has become the de-facto approach for object detection, and many probabilistic object detectors have …

Born Identity Network: Multi-way Counterfactual Map Generation to Explain a Classifier's Decision


Authors:  KwanseokOh, JeeSeokYoon, Heung-IlSuk....
Published date-11/20/2020

Abstract: There exists an apparent negative correlation between performance and interpretability of deep learning models. In an effort to reduce this negative correlation, we propose Born Identity Network (BIN), which is …

ATSal: An Attention Based Architecture for Saliency Prediction in 360 Videos


Authors:  YasserDahou, MarouaneTliba, KevinMcGuinness....
Published date-11/20/2020
Tasks:  SaliencyPrediction

Abstract: The spherical domain representation of 360 video/image presents many challenges related to the storage, processing, transmission and rendering of omnidirectional videos (ODV). Models of human visual attention can be used …

Assessing out-of-domain generalization for robust building damage detection


Authors:  VitusBenson, AlexanderEcker....
Published date-11/20/2020
Tasks:  DomainGeneralization

Abstract: An important step for limiting the negative impact of natural disasters is rapid damage assessment after a disaster occurred. For instance, building damage detection can be automated by applying computer …

Continuous Pruning of Deep Convolutional Networks Using Selective Weight Decay


Authors:  HugoTessier, VincentGripon, MathieuLéonardon....
Published date-11/20/2020
Tasks:  NetworkPruning

Abstract: During the last decade, deep convolutional networks have become the reference for many machine learning tasks, especially in computer vision. However, large computational needs make them hard to deploy on …

Filter by

Categories

Tags