Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations

1 code implementation • 25 Jan 2024 • Xinyue Xu, Yi Qin, Lu Mi, Hao Wang, Xiaomeng Li

Our ECBMs address both limitations of existing CBMs, providing higher accuracy and richer concept interpretations.

Dynamic Data Augmentation via MCTS for Prostate MRI Segmentation

1 code implementation • 25 May 2023 • Xinyue Xu, Yuhan Hsi, Haonan Wang, Xiaomeng Li

However, manually configuring a generic augmentation combination and parameters for different datasets is non-trivial due to inconsistent acquisition approaches and data distributions.

Data Augmentation MRI segmentation

Reliable and Efficient Evaluation of Adversarial Robustness for Deep Hashing-Based Retrieval

no code implementations • 22 Mar 2023 • Xunguang Wang, Jiawang Bai, Xinyue Xu, Xiaomeng Li

Deep hashing has been extensively applied to massive image retrieval due to its efficiency and effectiveness.

Adversarial Robustness Deep Hashing +2

Subgraph Frequency Distribution Estimation using Graph Neural Networks

no code implementations • 14 Jul 2022 • Zhongren Chen, Xinyue Xu, Shengyi Jiang, Hao Wang, Lu Mi

Small subgraphs (graphlets) are important features to describe fundamental units of a large network.

Task-Oriented Optimal Sequencing of Visualization Charts

1 code implementation • 7 Aug 2019 • Danqing Shi, Yang Shi, Xinyue Xu, Nan Chen, Siwei Fu, Hongjin Wu, Nan Cao

A chart sequence is used to describe a series of visualization charts generated in the exploratory analysis by data analysts.

Anomaly Detection