Home /
Research
Showing 103 - 108 / 897
Information Maximization for Few-Shot Learning
MalikBoudiaf, ImtiazZiko, JérômeRony....
Published date-12/01/2020
Few-ShotLearning, Meta-Learning
We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions for a given few-shot task, in conjunction …
ICNet: Intra-saliency Correlation Network for Co-Saliency Detection
Wen-DaJin, JunXu, Ming-MingCheng....
Published date-12/01/2020
SaliencyDetection
Intra-saliency and inter-saliency cues have been extensively studied for co-saliency detection (Co-SOD). Model-based methods produce coarse Co-SOD results due to hand-crafted intra- and inter-saliency features. Current data-driven models exploit inter-saliency …
MATE: Plugging in Model Awareness to Task Embedding for Meta Learning
XiaohanChen, ZhangyangWang, SiyuTang....
Published date-12/01/2020
FeatureSelection, Few-ShotLearning, Meta-Learning
Meta-learning improves generalization of machine learning models when faced with previously unseen tasks by leveraging experiences from different, yet related prior tasks. To allow for better generalization, we propose a …
Soft Contrastive Learning for Visual Localization
JanineThoma, DandaPaniPaudel, LucV.Gool....
Published date-12/01/2020
ContrastiveLearning, ImageRetrieval, VisualLocalization
Localization by image retrieval is inexpensive and scalable due to simple mapping and matching techniques. Such localization, however, depends upon the quality of image features often obtained using Contrastive learning …
SRG-Net: Unsupervised Segmentation for Terracotta Warrior Point Cloud with 3D Pointwise CNN methods
YaoHu, GuohuaGeng, KangLi....
Published date-12/01/2020
Clustering
In this paper, we present a seed-region-growing CNN(SRG-Net) for unsupervised part segmentation with 3D point clouds of terracotta warriors. Previous neural network researches in 3D are mainly about supervised classification, …
Lipschitz-Certifiable Training with a Tight Outer Bound
SungyoonLee, JaewookLee, SaeromPark....
Published date-12/01/2020
Verifiable training is a promising research direction for training a robust network. However, most verifiable training methods are slow or lack scalability. In this study, we propose a fast and …