1 code implementation • 30 Jun 2023 • Nazmul Karim, Abdullah Al Arafat, Umar Khalid, Zhishan Guo, Naznin Rahnavard
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.
1 code implementation • ICCV 2023 • Sabbir Ahmed, Abdullah Al Arafat, Mamshad Nayeem Rizve, Rahim Hossain, Zhishan Guo, Adnan Siraj Rakin
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.
1 code implementation • 19 Sep 2022 • Nicholas Gray, Megan Moraes, Jiang Bian, Alex Wang, Allen Tian, Kurt Wilson, Yan Huang, Haoyi Xiong, Zhishan Guo
It provides an essential enrichment to the widely used LISA Traffic Sign dataset.
1 code implementation • 21 Aug 2022 • Ashkan Farhangi, Jiang Bian, Arthur Huang, Haoyi Xiong, Jun Wang, Zhishan Guo
Moreover, the framework employs a dynamic uncertainty optimization algorithm that reduces the uncertainty of forecasts in an online manner.
1 code implementation • PAKDD 2022: Advances in Knowledge Discovery and Data Mining 2022 • Ashkan Farhangi, Ning Sui, Nan Hua, Haiyan Bai, Arthur Huang, Zhishan Guo
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
1 code implementation • 8 Mar 2022 • Ashkan Farhangi, Arthur Huang, Zhishan Guo
To this end, it is essential to develop an interpretable forecast model that supports managerial and organizational decision-making.
no code implementations • IEEE Real-Time Systems Symposium (RTSS) 2019 • Ashkan Farhangi, Jiang Bian, Jun Wang, Zhishan Guo
Under the big data era, there is a crucial need to improve the performance of storage systems for data-intensive applications.
no code implementations • 25 Apr 2017 • Haoyi Xiong, Wei Cheng, Wenqing Hu, Jiang Bian, Zhishan Guo
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.
no code implementations • ACM SIGKDD international conference on Knowledge discovery and data mining 2013 • Wei Cheng, Xiang Zhang, Zhishan Guo, Yubao Wu, Patrick F. Sullivan, Wei Wang
Moreover, relationships between instances in different domains may be associated with weights based on prior (partial) knowledge.