Copertina

Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Bareeva, Dilyara, Dreyer, Maximilian, Pahde, Frederik, Samek, Wojciech, Lapuschkin, Sebastian
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data
di: Pahde, Frederik, et al.
Pubblicazione: (2025)

Post-Hoc Concept Disentanglement: From Correlated to Isolated Concept Representations
di: Erogullari, Eren, et al.
Pubblicazione: (2025)

PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits
di: Dreyer, Maximilian, et al.
Pubblicazione: (2024)

Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations
di: Dreyer, Maximilian, et al.
Pubblicazione: (2023)

Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence
di: Pahde, Frederik, et al.
Pubblicazione: (2022)

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers
di: Vielhaben, Johanna, et al.
Pubblicazione: (2024)

Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples
di: Bouanani, Oussama, et al.
Pubblicazione: (2026)

Towards Visually Explaining Statistical Tests with Applications in Biomedical Imaging
di: Javanbakhat, Masoumeh, et al.
Pubblicazione: (2026)

Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP
di: Hufe, Lorenz, et al.
Pubblicazione: (2025)

Explainable concept mappings of MRI: Revealing the mechanisms underlying deep learning-based brain disease classification
di: Tinauer, Christian, et al.
Pubblicazione: (2024)

AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
di: Achtibat, Reduan, et al.
Pubblicazione: (2024)

Manipulating Feature Visualizations with Gradient Slingshots
di: Bareeva, Dilyara, et al.
Pubblicazione: (2024)

Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers
di: Hatefi, Sayed Mohammad Vakilzadeh, et al.
Pubblicazione: (2024)

Human-Centered Evaluation of XAI Methods
di: Dawoud, Karam, et al.
Pubblicazione: (2023)

Playing the network backward: A Game Theoretic Attribution Framework
di: Zimmermann, Jakob Paul, et al.
Pubblicazione: (2026)

Synthetic Generation of Dermatoscopic Images with GAN and Closed-Form Factorization
di: Mekala, Rohan Reddy, et al.
Pubblicazione: (2024)

XAI-guided Insulator Anomaly Detection for Imbalanced Datasets
di: Hoefler, Maximilian Andreas, et al.
Pubblicazione: (2024)

MAESTRO: Task-Relevant Optimization via Adaptive Feature Enhancement and Suppression for Multi-task 3D Perception
di: Kang, Changwon, et al.
Pubblicazione: (2025)

Quanda: An Interpretability Toolkit for Training Data Attribution Evaluation and Beyond
di: Bareeva, Dilyara, et al.
Pubblicazione: (2024)

Model Guidance via Explanations Turns Image Classifiers into Segmentation Models
di: Yu, Xiaoyan, et al.
Pubblicazione: (2024)

Deep Learning-based Multi Project InP Wafer Simulation for Unsupervised Surface Defect Detection
di: Cantú, Emílio Dolgener, et al.
Pubblicazione: (2025)

The Bias of Harmful Label Associations in Vision-Language Models
di: Hazirbas, Caner, et al.
Pubblicazione: (2024)

Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs
di: Tan, Xuwei, et al.
Pubblicazione: (2026)

From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation
di: Achtibat, Reduan, et al.
Pubblicazione: (2022)

Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning
di: Zhang, Jihai, et al.
Pubblicazione: (2024)

Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation
di: Cho, Yooshin, et al.
Pubblicazione: (2025)

ECQ$^{\text{x}}$: Explainability-Driven Quantization for Low-Bit and Sparse DNNs
di: Becking, Daniel, et al.
Pubblicazione: (2021)

From Attribution to Action: A Human-Centered Application of Activation Steering
di: Labarta, Tobias, et al.
Pubblicazione: (2026)

Low-Rank Adaptation with Task-Relevant Feature Enhancement for Fine-tuning Language Models
di: Li, Changqun, et al.
Pubblicazione: (2024)

Multi Attribute Bias Mitigation via Representation Learning
di: Dwivedi, Rajeev Ranjan, et al.
Pubblicazione: (2025)

BAdd: Bias Mitigation through Bias Addition
di: Sarridis, Ioannis, et al.
Pubblicazione: (2024)

Mitigating Low-Frequency Bias: Feature Recalibration and Frequency Attention Regularization for Adversarial Robustness
di: Zhang, Kejia, et al.
Pubblicazione: (2024)

On the Generation and Mitigation of Harmful Geometry in Image-to-3D Models
di: Liu, Yule, et al.
Pubblicazione: (2026)

Mitigating Bias Using Model-Agnostic Data Attribution
di: De Coninck, Sander, et al.
Pubblicazione: (2024)

Frequency Regulation for Exposure Bias Mitigation in Diffusion Models
di: Yu, Meng, et al.
Pubblicazione: (2025)

Common-Sense Bias Modeling for Classification Tasks
di: Zhang, Miao, et al.
Pubblicazione: (2024)

Fractional Diffusion Bridge Models
di: Nobis, Gabriel, et al.
Pubblicazione: (2025)

ViG-Bias: Visually Grounded Bias Discovery and Mitigation
di: Marani, Badr-Eddine, et al.
Pubblicazione: (2024)

Fair Diagnosis: Leveraging Causal Modeling to Mitigate Medical Bias
di: Tian, Bowei, et al.
Pubblicazione: (2024)

Mitigating Long-Tail Bias via Prompt-Controlled Diffusion Augmentation
di: Wijenayake, Buddhi, et al.
Pubblicazione: (2026)