A Super-pixel-based Approach to the Stable Interpretation of Neural Networks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Gong, Shizhan, Zhang, Jingwei, Dou, Qi, Farnia, Farzan
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Structured Gradient-based Interpretations via Norm-Regularized Adversarial Training
di: Gong, Shizhan, et al.
Pubblicazione: (2024)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Efficient Image Super-Resolution with Multi-Scale Spatial Adaptive Attention Networks
di: Rao, Sushi, et al.
Pubblicazione: (2026)

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

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

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

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

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

A Novel Coronary Artery Registration Method Based on Super-pixel Particle Swarm Optimization
di: Qi, Peng, et al.
Pubblicazione: (2025)

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

Adaptive Convolutional Neural Network for Image Super-resolution
di: Wu, Ziang, et al.
Pubblicazione: (2024)

HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution
di: Chu, Shu-Chuan, et al.
Pubblicazione: (2024)

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

One-Step Diffusion-based Real-World Image Super-Resolution with Visual Perception Distillation
di: Wu, Xue, et al.
Pubblicazione: (2025)

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

MDeRainNet: An Efficient Macro-pixel Image Rain Removal Network
di: Yan, Tao, et al.
Pubblicazione: (2024)

A Cosine Network for Image Super-Resolution
di: Tian, Chunwei, et al.
Pubblicazione: (2026)

BIAS: A Body-based Interpretable Active Speaker Approach
di: Roxo, Tiago, et al.
Pubblicazione: (2024)

Stable Diffusion with Continuous-time Neural Network
di: Horvath, Andras
Pubblicazione: (2024)

LinearSR: Unlocking Linear Attention for Stable and Efficient Image Super-Resolution
di: Li, Xiaohui, et al.
Pubblicazione: (2025)

Exploring the Interplay of Interpretability and Robustness in Deep Neural Networks: A Saliency-guided Approach
di: Guesmi, Amira, et al.
Pubblicazione: (2024)

Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization
di: Peng, Jingwei, et al.
Pubblicazione: (2025)

Spiking Meets Attention: Efficient Remote Sensing Image Super-Resolution with Attention Spiking Neural Networks
di: Xiao, Yi, et al.
Pubblicazione: (2025)

Increasing Interpretability of Neural Networks By Approximating Human Visual Saliency
di: Boyd, Aidan, et al.
Pubblicazione: (2024)

Ghost-dil-NetVLAD: A Lightweight Neural Network for Visual Place Recognition
di: Gong, Qingyuan, et al.
Pubblicazione: (2021)

Neural Garment Dynamic Super-Resolution
di: Zhang, Meng, et al.
Pubblicazione: (2024)