Ugochukwu Ejike Akpudo

12 papers A 1Misc 2Journal 8Unranked 1
YearRankTypeTitle / Venue / Authors
2025 J jnl
CoPISan: Contrastive Perceptual Inference and Sanity Checks for Concept-Based CNN Explanations.
IEEE Trans. Pattern Anal. Mach. Intell.
Ugochukwu Ejike Akpudo, Yongsheng Gao, Jun Zhou, Andrew Lewis
2025 J jnl
TraNCE: Transformative Non-linear Concept Explainer for CNNs.
CoRR
Ugochukwu Ejike Akpudo, Yongsheng Gao, Jun Zhou, Andrew Lewis
2025 J jnl
TraNCE: Transformative Nonlinear Concept Explainer for CNNs.
IEEE Trans. Neural Networks Learn. Syst.
Ugochukwu Ejike Akpudo, Yongsheng Gao, Jun Zhou, Andrew Lewis
2025 J jnl
Visual Explanation via Similar Feature Activation for Metric Learning.
CoRR
Yi Liao, Ugochukwu Ejike Akpudo, Jue Zhang, Yongsheng Gao, Jun Zhou, Wenyi Zeng, Weichuan Zhang
2024 A conf
Coherentice: Invertible Concept-Based Explainability Framework for CNNs beyond Fidelity.
ICME
Ugochukwu Ejike Akpudo, Yongsheng Gao, Jun Zhou, Andrew Lewis
2023 Misc conf
NCAF: NTD-based Concept Activation Factorisation Framework for CNN Explainability.
IVCNZ
Ugochukwu Ejike Akpudo, Xiaohan Yu, Jun Zhou, Yongsheng Gao
2023 Misc conf
What EXACTLY are We Looking at?: Investigating for Discriminance in Ultra-Fine-Grained Visual Categorization Tasks.
DICTA
Ugochukwu Ejike Akpudo, Xiaohan Yu, Jun Zhou, Yongsheng Gao
2022 J jnl
A Cost-Efficient MCSA-Based Fault Diagnostic Framework for SCIM at Low-Load Conditions.
Algorithms
Chibuzo Nwabufo Okwuosa, Ugochukwu Ejike Akpudo, Jang-Wook Hur
2022 J jnl
Exploring the Efficiencies of Spectral Isolation for Intelligent Wear Monitoring of Micro Drill Bit Automatic Regrinding In-Line Systems.
Algorithms
Ugochukwu Ejike Akpudo, Jang-Wook Hur
2021 J jnl
An Automated Sensor Fusion Approach for the RUL Prediction of Electromagnetic Pumps.
IEEE Access
Ugochukwu Ejike Akpudo, Hur Jang-Wook
2020 J jnl
A Multi-Domain Diagnostics Approach for Solenoid Pumps Based on Discriminative Features.
IEEE Access
Ugochukwu Ejike Akpudo, Hur Jang-Wook
2020 — conf
Intelligent Solenoid Pump Fault Detection based on MFCC Features, LLE and SVM
ICAIIC
Ugochukwu Ejike Akpudo, Jang-Wook Hur