Cover Image

Structured Gradient-based Interpretations via Norm-Regularized Adversarial Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gong, Shizhan, Dou, Qi, Farnia, Farzan
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Super-pixel-based Approach to the Stable Interpretation of Neural Networks
by: Gong, Shizhan, et al.
Published: (2024)

Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models
by: Gong, Shizhan, et al.
Published: (2025)

Sparse Domain Transfer via Elastic Net Regularization
by: Zhang, Jingwei, et al.
Published: (2024)

Interpretation of Neural Networks is Susceptible to Universal Adversarial Perturbations
by: Oskouie, Haniyeh Ehsani, et al.
Published: (2022)

Concepts from Representations: Post-hoc Concept Bottleneck Models via Sparse Decomposition of Visual Representations
by: Gong, Shizhan, et al.
Published: (2026)

Gaussian Smoothing in Saliency Maps: The Stability-Fidelity Trade-Off in Neural Network Interpretability
by: Ye, Zhuorui, et al.
Published: (2024)

Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward
by: Gong, Shizhan, et al.
Published: (2026)

An Interpretable Evaluation of Entropy-based Novelty of Generative Models
by: Zhang, Jingwei, et al.
Published: (2024)

Scendi Score: Prompt-Aware Diversity Evaluation via Schur Complement of CLIP Embeddings
by: Ospanov, Azim, et al.
Published: (2024)

Boosting Adversarial Training via Fisher-Rao Norm-based Regularization
by: Yin, Xiangyu, et al.
Published: (2024)

Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean Discrepancy Guidance
by: Sani, Matina Mahdizadeh, et al.
Published: (2026)

When Exploration Comes for Free with Mixture-Greedy: Do we need UCB in Diversity-Aware Multi-Armed Bandits?
by: Nia, Bahar Dibaei, et al.
Published: (2026)

PromptSplit: Revealing Prompt-Level Disagreement in Generative Models
by: Lotfian, Mehdi, et al.
Published: (2026)

SPARKE: Scalable Prompt-Aware Diversity and Novelty Guidance in Diffusion Models via RKE Score
by: Jalali, Mohammad, et al.
Published: (2025)

Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization
by: Liu, Yujia, et al.
Published: (2024)

Exposing Diversity Bias in Deep Generative Models: Statistical Origins and Correction of Diversity Error
by: Farnia, Farzan, et al.
Published: (2026)

Unveiling Differences in Generative Models: A Scalable Differential Clustering Approach
by: Zhang, Jingwei, et al.
Published: (2024)

ACCORD: Alleviating Concept Coupling through Dependence Regularization for Text-to-Image Diffusion Personalization
by: Liu, Shizhan, et al.
Published: (2025)

Physical Adversarial Camouflage through Gradient Calibration and Regularization
by: Liang, Jiawei, et al.
Published: (2025)

3DSAM-adapter: Holistic adaptation of SAM from 2D to 3D for promptable tumor segmentation
by: Gong, Shizhan, et al.
Published: (2023)

Towards an Explainable Comparison and Alignment of Feature Embeddings
by: Jalali, Mohammad, et al.
Published: (2025)

Conditional Vendi Score: An Information-Theoretic Approach to Diversity Evaluation of Prompt-based Generative Models
by: Jalali, Mohammad, et al.
Published: (2024)

DiffPattern-Flex: Efficient Layout Pattern Generation via Discrete Diffusion
by: Wang, Zixiao, et al.
Published: (2025)

Boosting Adversarial Transferability via Commonality-Oriented Gradient Optimization
by: Gao, Yanting, et al.
Published: (2025)

Training-Free and Interpretable Hateful Video Detection via Multi-stage Adversarial Reasoning
by: Yang, Shuonan, et al.
Published: (2026)

Releasing Inequality Phenomenon in $\ell_{\infty}$-norm Adversarial Training via Input Gradient Distillation
by: Chen, Junxi, et al.
Published: (2023)

SORA: Free Second-Order Attacks in Fast Adversarial Training
by: Teymourian, Mazdak, et al.
Published: (2026)

pFedFair: Towards Optimal Group Fairness-Accuracy Trade-off in Heterogeneous Federated Learning
by: Lei, Haoyu, et al.
Published: (2025)

Low-Rank Tensor Recovery via Variational Schatten-p Quasi-Norm and Jacobian Regularization
by: Cheng, Zhengyun, et al.
Published: (2025)

GReAT: A Graph Regularized Adversarial Training Method
by: Bayram, Samet, et al.
Published: (2023)

Nexar Dashcam Collision Prediction Dataset and Challenge
by: Moura, Daniel C., et al.
Published: (2025)

RoMA: Robust Malware Attribution via Byte-level Adversarial Training with Global Perturbations and Adversarial Consistency Regularization
by: Sun, Yuxia, et al.
Published: (2025)

Fast Image-based Neural Relighting with Translucency-Reflection Modeling
by: Zhu, Shizhan, et al.
Published: (2023)

Contextual Interaction via Primitive-based Adversarial Training For Compositional Zero-shot Learning
by: Li, Suyi, et al.
Published: (2024)

MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks
by: Li, Mingsong, et al.
Published: (2025)

SARA: Structural and Adversarial Representation Alignment for Training-efficient Diffusion Models
by: Chen, Hesen, et al.
Published: (2025)

Adaptive Discriminative Regularization for Visual Classification
by: Zhao, Qingsong, et al.
Published: (2022)

LTD: Low Temperature Distillation for Gradient Masking-free Adversarial Training
by: Chen, Erh-Chung, et al.
Published: (2021)

VoxNeuS: Enhancing Voxel-Based Neural Surface Reconstruction via Gradient Interpolation
by: Liu, Sidun, et al.
Published: (2024)

Improving Adversarial Robustness of Attribution via Implicit Regularization
by: Mehrpanah, Amir, et al.
Published: (2026)