Home /

Research

Showing 169 - 174 / 897

FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training


Authors:  YongganFu, HaoranYou, YangZhao....
Published date-12/01/2020
Tasks:  Quantization

Abstract: Recent breakthroughs in deep neural networks (DNNs) have fueled a tremendous demand for intelligent edge devices featuring on-site learning, while the practical realization of such systems remains a challenge due …

Field-wise Learning for Multi-field Categorical Data


Authors:  ZhibinLi, JianZhang, YongshunGong....
Published date-12/01/2020

Abstract: We propose a new method for learning with multi-field categorical data. Multi-field categorical data are usually collected over many heterogeneous groups. These groups can reflect in the categories under a …

Beta R-CNN: Looking into Pedestrian Detection from Another Perspective


Authors:  ZixuanXu, BanghuaiLi, YeYuan....
Published date-12/01/2020
Tasks:  PedestrianDetection

Abstract: Recently significant progress has been made in pedestrian detection, but it remains challenging to achieve high performance in occluded and crowded scenes. It could be mostly attributed to the widely …

Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D


Authors:  AnkitGoyal, KaiyuYang, DaweiYang....
Published date-12/01/2020

Abstract: Understanding spatial relations (e.g., laptop on table) in visual input is important for both humans and robots. Existing datasets are insufficient as they lack large-scale, high-quality 3D ground truth information, …

Analysis of Drifting Features


Authors:  FabianHinder, JonathanJakob, BarbaraHammer....
Published date-12/01/2020
Tasks:  FeatureSelection

Abstract: The notion of concept drift refers to the phenomenon that the distribution, which is underlying the observed data, changes over time. We are interested in an identification of those features, …

HRN: A Holistic Approach to One Class Learning


Authors:  WenpengHu, MengyuWang, QiQin....
Published date-12/01/2020
Tasks:  AnomalyDetection, ImageClassification

Abstract: Existing neural network based one-class learning methods mainly use various forms of auto-encoders or GAN style adversarial training to learn a latent representation of the given one class of data. …

Filter by

Categories

Tags