conftrace_

perturbation-based method

10 papers

Explore in graph

Co-occurring keywords · papers mentioning both

neural network (2) gradient-based method (2) explainable ai (2) feature learning (2) expected risk minimization (1) graph neural network (1) heatmap visualization (1) time series deep learning (1) reliable edge mining (1) closed-form expression (1)

Papers

FiMMIA: scaling semantic perturbation-based membership inference across modalities EACL 2026 Occlusion Sensitivity Analysis With Augmentation Subspace Perturbation in Deep Feature Space WACV 2024 SampDetox: Black-box Backdoor Defense via Perturbation-based Sample Detoxification NeurIPS 2024 Validation, Robustness, and Accuracy of Perturbation-Based Sensitivity Analysis Methods for Time-Series Deep Learning Models AAAI 2024 Dual Perspective of Label-Specific Feature Learning for Multi-Label Classification ICML 2022 OccAM's Laser: Occlusion-Based Attribution Maps for 3D Object Detectors on LiDAR Data CVPR 2022 A Novel Visual Interpretability for Deep Neural Networks by Optimizing Activation Maps with Perturbation AAAI 2021 Explaining Errors in Machine Translation with Absolute Gradient Ensembles EMNLP 2021 Towards the Unification and Robustness of Perturbation and Gradient Based Explanations ICML 2021 Data-Efficient Semi-Supervised Learning by Reliable Edge Mining CVPR 2020