Search Results for author:
Found 9 papers, 6 papers with code
Efficient Backdoor Removal Through Natural Gradient Fine-tuning
Extensive experiments show that the proposed method achieves state-of-the-art performance on a wide range of backdoor defense benchmarks: four different datasets- CIFAR10, GTSRB, Tiny-ImageNet, and ImageNet; 13 recent backdoor attacks, e. g.
SSDA: Secure Source-Free Domain Adaptation
Source-free domain adaptation (SFDA) is a popular unsupervised domain adaptation method where a pre-trained model from a source domain is adapted to a target domain without accessing any source data.
GLARE: A Dataset for Traffic Sign Detection in Sun Glare
It provides an essential enrichment to the widely used LISA Traffic Sign dataset.
AA-Forecast: Anomaly-Aware Forecast for Extreme Events
Moreover, the framework employs a dynamic uncertainty optimization algorithm that reduces the uncertainty of forecasts in an online manner.
Protoformer: Embedding Prototypes for Transformers
This paper proposes Protoformer, a novel self-learning framework for Transformers that can leverage problematic samples for text classification.
Ranked #1 on
Text Classification
on arXiv-10
A Novel Deep Learning Model for Hotel Demand and Revenue Prediction amid COVID-19
To this end, it is essential to develop an interpretable forecast model that supports managerial and organizational decision-making.
Work-in-progress: a deep learning strategy for I/O scheduling in storage systems
Under the big data era, there is a crucial need to improve the performance of storage systems for data-intensive applications.
FWDA: a Fast Wishart Discriminant Analysis with its Application to Electronic Health Records Data Classification
Classical LDA for EHR data classification, however, suffers from two handicaps: the ill-posed estimation of LDA parameters (e. g., covariance matrix), and the "linear inseparability" of EHR data.
Flexible and Robust Co-Regularized Multi-Domain Graph Clustering.
Moreover, relationships between instances in different domains may be associated with weights based on prior (partial) knowledge.
