Image de couverture de livre

Single-weight Model Editing for Post-hoc Spurious Correlation Neutralization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hakemi, Shahin, Akhtar, Naveed, Hassan, Ghulam Mubashar, Mian, Ajmal
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Deeper Diffusion Models Amplify Bias
par: Hakemi, Shahin, et autres
Publié: (2025)

DRBD-Mamba for Robust and Efficient Brain Tumor Segmentation with Analytical Insights
par: Ali, Danish, et autres
Publié: (2025)

D3Seg: Dependency-Aware Diffusion for Brain Tumor Segmentation with Missing Modalities
par: Ali, Danish, et autres
Publié: (2026)

Modeling Human Skeleton Joint Dynamics for Fall Detection
par: Zahan, Sania, et autres
Publié: (2025)

SDFA: Structure Aware Discriminative Feature Aggregation for Efficient Human Fall Detection in Video
par: Zahan, Sania, et autres
Publié: (2025)

Occlusion-aware Text-Image-Point Cloud Pretraining for Open-World 3D Object Recognition
par: Nguyen, Khanh, et autres
Publié: (2025)

Retrieving Objects from 3D Scenes with Box-Guided Open-Vocabulary Instance Segmentation
par: Nguyen, Khanh, et autres
Publié: (2025)

RI-Mamba: Rotation-Invariant Mamba for Robust Text-to-Shape Retrieval
par: Nguyen, Khanh, et autres
Publié: (2026)

M3BUNet: Mobile Mean Max UNet for Pancreas Segmentation on CT-Scans
par: juwita, Juwita, et autres
Publié: (2024)

DDB: Diffusion Driven Balancing to Address Spurious Correlations
par: Parast, Aryan Yazdan, et autres
Publié: (2025)

Manipulating and Mitigating Generative Model Biases without Retraining
par: Vice, Jordan, et autres
Publié: (2024)

Exploring Bias in over 100 Text-to-Image Generative Models
par: Vice, Jordan, et autres
Publié: (2025)

Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction
par: Vice, Jordan, et autres
Publié: (2024)

On the Reliability of Vision-Language Models Under Adversarial Frequency-Domain Perturbations
par: Vice, Jordan, et autres
Publié: (2025)

Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors
par: Yang, Peiyu, et autres
Publié: (2026)

Dynamic watermarks in images generated by diffusion models
par: Chen, Yunzhuo, et autres
Publié: (2025)

Deepfake Detection with Spatio-Temporal Consistency and Attention
par: Chen, Yunzhuo, et autres
Publié: (2025)

On the Fairness, Diversity and Reliability of Text-to-Image Generative Models
par: Vice, Jordan, et autres
Publié: (2024)

Multistream Network for LiDAR and Camera-based 3D Object Detection in Outdoor Scenes
par: Ibrahim, Muhammad, et autres
Publié: (2025)

Simultaneous Multiple Object Detection and Pose Estimation using 3D Model Infusion with Monocular Vision
par: Li, Congliang, et autres
Publié: (2022)

CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation
par: Liang, Li, et autres
Publié: (2025)

Mitigating Memorization in Text-to-Image Diffusion via Region-Aware Prompt Augmentation and Multimodal Copy Detection
par: Chen, Yunzhuo, et autres
Publié: (2026)

HSFM: Hard-Set-Guided Feature-Space Meta-Learning for Robust Classification under Spurious Correlations
par: Parast, Aryan Yazdan, et autres
Publié: (2026)

Skip Mamba Diffusion for Monocular 3D Semantic Scene Completion
par: Liang, Li, et autres
Publié: (2025)

Implicit Neural Representation-Based Continuous Single Image Super-Resolution: An Empirical Benchmark
par: Nasir, Tayyab, et autres
Publié: (2026)

SCTransNet: Spatial-channel Cross Transformer Network for Infrared Small Target Detection
par: Yuan, Shuai, et autres
Publié: (2024)

Context-guided Responsible Data Augmentation with Diffusion Models
par: Islam, Khawar, et autres
Publié: (2025)

GenMix: Effective Data Augmentation with Generative Diffusion Model Image Editing
par: Islam, Khawar, et autres
Publié: (2024)

Efficient Diffusion Models for Vision: A Survey
par: Ulhaq, Anwaar, et autres
Publié: (2022)

Multi-scale Coarse-to-fine Modeling for Test-time Human Motion Control
par: Le, Nhat, et autres
Publié: (2026)

Avatar Concept Slider: Controllable Editing of Concepts in 3D Human Avatars
par: Foo, Lin Geng, et autres
Publié: (2024)

Class-Partitioned VQ-VAE and Latent Flow Matching for Point Cloud Scene Generation
par: Edirimuni, Dasith de Silva, et autres
Publié: (2026)

Mantis: Mamba-native Tuning is Efficient for 3D Point Cloud Foundation Models
par: Guo, Zihao, et autres
Publié: (2026)

FastBO: Fast HPO and NAS with Adaptive Fidelity Identification
par: Jiang, Jiantong, et autres
Publié: (2024)

Reducing Spurious Correlation for Federated Domain Generalization
par: Ma, Shuran, et autres
Publié: (2024)

Focusing Image Generation to Mitigate Spurious Correlations
par: Li, Xuewei, et autres
Publié: (2024)

Plug-and-Play Interpretable Responsible Text-to-Image Generation via Dual-Space Multi-facet Concept Control
par: Azam, Basim, et autres
Publié: (2025)

Suitability of KANs for Computer Vision: A preliminary investigation
par: Azam, Basim, et autres
Publié: (2024)

Learning Generalizable Models via Disentangling Spurious and Enhancing Potential Correlations
par: Wang, Na, et autres
Publié: (2024)

Post-hoc Part-prototype Networks
par: Tan, Andong, et autres
Publié: (2024)