Search Results for author: Yi Yao

Found 12 papers, 1 papers with code

Trigger Hunting with a Topological Prior for Trojan Detection

no code implementations ICLR 2022 Xiaoling Hu, Xiao Lin, Michael Cogswell, Yi Yao, Susmit Jha, Chao Chen

Despite their success and popularity, deep neural networks (DNNs) are vulnerable when facing backdoor attacks.

Improving Users' Mental Model with Attention-directed Counterfactual Edits

no code implementations13 Oct 2021 Kamran Alipour, Arijit Ray, Xiao Lin, Michael Cogswell, Jurgen P. Schulze, Yi Yao, Giedrius T. Burachas

In the domain of Visual Question Answering (VQA), studies have shown improvement in users' mental model of the VQA system when they are exposed to examples of how these systems answer certain Image-Question (IQ) pairs.

Question Answering Retrieval +2

Modular Adaptation for Cross-Domain Few-Shot Learning

1 code implementation1 Apr 2021 Xiao Lin, Meng Ye, Yunye Gong, Giedrius Buracas, Nikoletta Basiou, Ajay Divakaran, Yi Yao

Adapting pre-trained representations has become the go-to recipe for learning new downstream tasks with limited examples.

cross-domain few-shot learning Representation Learning

Machine Learning Applications on Neuroimaging for Diagnosis and Prognosis of Epilepsy: A Review

no code implementations5 Feb 2021 Jie Yuan, Xuming Ran, Keyin Liu, Chen Yao, Yi Yao, Haiyan Wu, Quanying Liu

Machine learning is playing an increasingly important role in medical image analysis, spawning new advances in the clinical application of neuroimaging.

BIG-bench Machine Learning Electroencephalogram (EEG) +1

The Impact of Explanations on AI Competency Prediction in VQA

no code implementations2 Jul 2020 Kamran Alipour, Arijit Ray, Xiao Lin, Jurgen P. Schulze, Yi Yao, Giedrius T. Burachas

In this paper, we evaluate the impact of explanations on the user's mental model of AI agent competency within the task of visual question answering (VQA).

Language Modelling Question Answering +2

Progressive Growing of Neural ODEs

no code implementations ICLR Workshop DeepDiffEq 2019 Hammad A. Ayyubi, Yi Yao, Ajay Divakaran

Neural Ordinary Differential Equations (NODEs) have proven to be a powerful modeling tool for approximating (interpolation) and forecasting (extrapolation) irregularly sampled time series data.

Time Series Forecasting

Can You Explain That? Lucid Explanations Help Human-AI Collaborative Image Retrieval

no code implementations5 Apr 2019 Arijit Ray, Yi Yao, Rakesh Kumar, Ajay Divakaran, Giedrius Burachas

Our experiments, therefore, demonstrate that ExAG is an effective means to evaluate the efficacy of AI-generated explanations on a human-AI collaborative task.

Image Retrieval Question Answering +3

Stacked Spatio-Temporal Graph Convolutional Networks for Action Segmentation

no code implementations26 Nov 2018 Pallabi Ghosh, Yi Yao, Larry S. Davis, Ajay Divakaran

We show results on CAD120 (which provides pre-computed node features and edge weights for fair performance comparison across algorithms) as well as a more complex real-world activity dataset, Charades.

Action Recognition Action Segmentation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.