Home /
Research
Showing 181 - 186 / 904
Unsupervised Anomaly Detection From Semantic Similarity Scores
NimaRafiee, RahilGholamipoor, MarkusKollmann....
Published date-12/01/2020
AnomalyDetection, Out-of-DistributionDetection, SemanticSimilarity, SemanticTextualSimilarity, UnsupervisedAnomalyDetection
In this paper, we present SemSAD, a simple and generic framework for detecting examples that lie out-of-distribution (OOD) for a given training set. The approach is based on learning a …
Adversarial Learning for Robust Deep Clustering
XuYang, ChengDeng, KunWei....
Published date-12/01/2020
AdversarialAttack, Clustering, DeepClustering
Deep clustering integrates embedding and clustering together to obtain the optimal nonlinear embedding space, which is more effective in real-world scenarios compared with conventional clustering methods. However, the robustness of …
Learning sparse codes from compressed representations with biologically plausible local wiring constraints
KionFallah, AdamWillats, NinghaoLiu....
Published date-12/01/2020
DimensionalityReduction
Sparse coding is an important method for unsupervised learning of task-independent features in theoretical neuroscience models of neural coding. While a number of algorithms exist to learn these representations from …
How Can I Explain This to You? An Empirical Study of Deep Neural Network Explanation Methods
JeyaVikranthJeyakumar, JosephNoor, Yu-HsiCheng....
Published date-12/01/2020
SentimentAnalysis
Explaining the inner workings of deep neural network models have received considerable attention in recent years. Researchers have attempted to provide human parseable explanations justifying why a model performed a …
The Dilemma of TriHard Loss and an Element-Weighted TriHard Loss for Person Re-Identification
YihaoLv, YouzhiGu, LiuXinggao....
Published date-12/01/2020
PersonRe-Identification
Triplet loss with batch hard mining (TriHard loss) is an important variation of triplet loss inspired by the idea that hard triplets improve the performance of metric leaning networks. However, …
Neuron-level Structured Pruning using Polarization Regularizer
TaoZhuang, ZhixuanZhang, YuhengHuang....
Published date-12/01/2020
Neuron-level structured pruning is a very effective technique to reduce the computation of neural networks without compromising prediction accuracy. In previous works, structured pruning is usually achieved by imposing L1 …