Home /

Research

Showing 367 - 372 / 897

Robust Gaussian Process Regression Based on Iterative Trimming

Authors:  Zhao-ZhouLi, LuLi, ZhengyiShao....
Published date-11/22/2020
Gaussian Process
Graph Embeddings
LINE
Non-Parametric Classification

Abstract: The model prediction of the Gaussian process (GP) regression can be significantly biased when the data are contaminated by outliers. We propose a new robust GP regression algorithm that iteratively …
Paper Code

Learning a Deep Generative Model like a Program: the Free Category Prior

Authors:  EliSennesh....
Published date-11/22/2020
Tasks:  Programinduction

Abstract: Humans surpass the cognitive abilities of most other animals in our ability to "chunk" concepts into words, and then combine the words to combine the concepts. In this process, we …
Paper Code

Dense open-set recognition with synthetic outliers generated by Real NVP

Authors:  MatejGrcić, PetraBevandić, SinišaŠegvić....
Published date-11/22/2020
Tasks:  AutonomousDriving, ImageClassification, OpenSetLearning, OutlierDetection, SemanticSegmentation

Abstract: Today's deep models are often unable to detect inputs which do not belong to the training distribution. This gives rise to confident incorrect predictions which could lead to devastating consequences …
Paper Code

LRTA: A Transparent Neural-Symbolic Reasoning Framework with Modular Supervision for Visual Question Answering

Authors:  WeixinLiang, FeiyangNiu, AishwaryaReganti....
Published date-11/21/2020
Tasks:  QuestionAnswering, VisualQuestionAnswering

Abstract: The predominant approach to visual question answering (VQA) relies on encoding the image and question with a "black-box" neural encoder and decoding a single token as the answer like "yes" …
Paper Code

One Metric to Measure them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection Tasks

Authors:  KemalOksuz, BarisCanCam, SinanKalkan....
Published date-11/21/2020
Tasks:  InstanceSegmentation, KeypointDetection, ObjectDetection, PanopticSegmentation, SemanticSegmentation

Abstract: Despite being widely used as a performance measure for visual detection tasks, Average Precision (AP) is limited in (i) including localisation quality, (ii) interpretability and (iii) applicability to outputs without …
Paper Code

DmifNet:3D Shape Reconstruction Based on Dynamic Multi-Branch Information Fusion

Authors:  LeiLI, SupingWu....
Published date-11/21/2020
Tasks:  3DObjectReconstruction, 3DShapeReconstruction, DomainAdaptation, ObjectReconstruction

Abstract: 3D object reconstruction from a single-view image is a long-standing challenging problem. Previous work was difficult to accurately reconstruct 3D shapes with a complex topology which has rich details at …
Paper Code

Filter by

Categories

Tags