Imagen de Portada

Class Unlearning via Depth-Aware Removal of Forget-Specific Directions

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hatami, Arman, Aalishah, Romina, Monosov, Ilya E.
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Deep Unlearning: Fast and Efficient Gradient-free Approach to Class Forgetting
por: Kodge, Sangamesh, et al.
Publicado: (2023)

Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning
por: Fan, Chongyu, et al.
Publicado: (2024)

Multi-Class Unlearning for Image Classification via Weight Filtering
por: Poppi, Samuele, et al.
Publicado: (2023)

The Illusion of Forgetting: Attack Unlearned Diffusion via Initial Latent Variable Optimization
por: Li, Manyi, et al.
Publicado: (2026)

Merging without Forgetting: Continual Fusion of Task-Specific Models via Optimal Transport
por: Pan, Zecheng, et al.
Publicado: (2025)

Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning
por: Paramonov, Kirill, et al.
Publicado: (2025)

To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models
por: Tian, Bozhong, et al.
Publicado: (2024)

Sculpting Memory: Multi-Concept Forgetting in Diffusion Models via Dynamic Mask and Concept-Aware Optimization
por: Li, Gen, et al.
Publicado: (2025)

CCSI: Continual Class-Specific Impression for Data-free Class Incremental Learning
por: Ayromlou, Sana, et al.
Publicado: (2024)

Dynamic Integration of Task-Specific Adapters for Class Incremental Learning
por: Li, Jiashuo, et al.
Publicado: (2024)

Catastrophic Forgetting Mitigation via Discrepancy-Weighted Experience Replay
por: Xu, Xinrun, et al.
Publicado: (2025)

Latest Advancements Towards Catastrophic Forgetting under Data Scarcity: A Comprehensive Survey on Few-Shot Class Incremental Learning
por: Ma'sum, M. Anwar, et al.
Publicado: (2025)

Face Identity Unlearning for Retrieval via Embedding Dispersion
por: Zakharov, Mikhail
Publicado: (2025)

Hypnopaedia-Aware Machine Unlearning via Psychometrics of Artificial Mental Imagery
por: Chang, Ching-Chun, et al.
Publicado: (2024)

Toxicity Assessment in Preclinical Histopathology via Class-Aware Mahalanobis Distance for Known and Novel Anomalies
por: Graf, Olga, et al.
Publicado: (2026)

CoUn: Empowering Machine Unlearning via Contrastive Learning
por: Khalil, Yasser H., et al.
Publicado: (2025)

Learning from Oblivion: Predicting Knowledge Overflowed Weights via Retrodiction of Forgetting
por: Jang, Jinhyeok, et al.
Publicado: (2025)

Merge and Bound: Direct Manipulations on Weights for Class Incremental Learning
por: Kim, Taehoon, et al.
Publicado: (2025)

Bias-Aware Machine Unlearning: Towards Fairer Vision Models via Controllable Forgetting
por: Aylapuram, Sai Siddhartha Chary, et al.
Publicado: (2025)

The Effectiveness of Random Forgetting for Robust Generalization
por: Ramkumar, Vijaya Raghavan T, et al.
Publicado: (2024)

Slowing Down Forgetting in Continual Learning
por: Janetzky, Pascal, et al.
Publicado: (2024)

DMODE: Differential Monocular Object Distance Estimation Module without Class Specific Information
por: Agand, Pedram, et al.
Publicado: (2022)

Adapt then Unlearn: Exploring Parameter Space Semantics for Unlearning in Generative Adversarial Networks
por: Tiwary, Piyush, et al.
Publicado: (2023)

Concept Unlearning via Cross-Attention Activation Projection for Diffusion Models
por: Moon, Saemi, et al.
Publicado: (2026)

ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition
por: Lin, Shen, et al.
Publicado: (2026)

CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic
por: Lin, Shen, et al.
Publicado: (2026)

Mitigating Catastrophic Forgetting and Mode Collapse in Text-to-Image Diffusion via Latent Replay
por: Otani, Aoi
Publicado: (2025)

Controllable Unlearning for Image-to-Image Generative Models via $\varepsilon$-Constrained Optimization
por: Feng, Xiaohua, et al.
Publicado: (2024)

Unlearning-based Neural Interpretations
por: Choi, Ching Lam, et al.
Publicado: (2024)

ReDepth Anything: Test-Time Depth Refinement via Self-Supervised Re-lighting
por: Bhattarai, Ananta R., et al.
Publicado: (2025)

Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning
por: Sun, Hai-Long, et al.
Publicado: (2025)

T2ID-CAS: Diffusion Model and Class Aware Sampling to Mitigate Class Imbalance in Neck Ultrasound Anatomical Landmark Detection
por: Varaganti, Manikanta, et al.
Publicado: (2025)

Practical Continual Forgetting for Pre-trained Vision Models
por: Zhao, Hongbo, et al.
Publicado: (2025)

Gradient Correlation Subspace Learning against Catastrophic Forgetting
por: Dubnov, Tammuz, et al.
Publicado: (2024)

Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs
por: Fang, Xianya, et al.
Publicado: (2026)

Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking
por: Deng, Kaiyuan, et al.
Publicado: (2026)

Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Images
por: Bonato, Jacopo, et al.
Publicado: (2024)

Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions
por: Baumann, Stefan Andreas, et al.
Publicado: (2024)

Few-Shot Class Incremental Learning with Attention-Aware Self-Adaptive Prompt
por: Liu, Chenxi, et al.
Publicado: (2024)

Efficient Document Image Dewarping via Hybrid Deep Learning and Cubic Polynomial Geometry Restoration
por: Istomin, Valery, et al.
Publicado: (2025)