Balancing clean accuracy and gradient robustness via mask-guided mixup and adaptive label refinement
- 11 August 2026
- journal article
- research article
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 20 (10) , 570
Abstract
No abstract availableKeywords
Funding Information
- The Research Projects of Ordinary Universities in Guangdong Province (2023KTSCX133)
- The Guangdong Ordinary University Key Laboratory (2021KSYS008)
- the Guangdong Basic and Applied Basic Research Foundation (2022A1515140103)
This publication has 14 references indexed in Scilit:
- An Explainable KAN–Shapley Framework for Many-to-Many Electric Vehicle Charging Dispatch in Intelligent Transportation SystemsIEEE Transactions on Intelligent Transportation Systems, 2026
- RealExp: Decoupling correlation bias in Shapley values for faithful model interpretationsInformation Processing & Management, 2025
- Illuminating the black box: An interpretable machine learning based on ensemble treesExpert Systems with Applications, 2025
- MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model2024
- Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement2024
- DeepMatcher: A deep transformer-based network for robust and accurate local feature matchingExpert Systems with Applications, 2023
- TransMix: Attend to Mix for Vision Transformers2022
- Attentive Cutmix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification2020
- CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features2019
- Deep Residual Learning for Image Recognition2016