Cover Image

Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Yu, Zheng, Dian, Mo, Qijie, Lu, Renjie, Lin, Kun-Yu, Zheng, Wei-Shi
Format:	Preprint
Published:	2025
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

You Only Erase Once: Erasing Anything without Bringing Unexpected Content
by: Zhu, Yixing, et al.
Published: (2026)

Erase at the Core: Representation Unlearning for Machine Unlearning
by: Lee, Jaewon, et al.
Published: (2026)

Human-Centric Transformer for Domain Adaptive Action Recognition
by: Lin, Kun-Yu, et al.
Published: (2024)

PRET: Planning with Directed Fidelity Trajectory for Vision and Language Navigation
by: Lu, Renjie, et al.
Published: (2024)

Generative Unlearning for Any Identity
by: Seo, Juwon, et al.
Published: (2024)

Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object Detection
by: Mo, Qijie, et al.
Published: (2024)

EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing
by: Fu, Yang, et al.
Published: (2026)

Erasing Concepts, Steering Generations: A Comprehensive Survey of Concept Suppression
by: Xie, Yiwei, et al.
Published: (2025)

MagicEraser: Erasing Any Objects via Semantics-Aware Control
by: Li, Fan, et al.
Published: (2024)

ProEdit: Inversion-based Editing From Prompts Done Right
by: Ouyang, Zhi, et al.
Published: (2025)

BlindU: Blind Machine Unlearning without Revealing Erasing Data
by: Wang, Weiqi, et al.
Published: (2026)

Towards Completeness: A Generalizable Action Proposal Generator for Zero-Shot Temporal Action Localization
by: Du, Jia-Run, et al.
Published: (2024)

Task-Oriented 6-DoF Grasp Pose Detection in Clutters
by: Wang, An-Lan, et al.
Published: (2025)

CoopDiff: Anticipating 3D Human-object Interactions via Contact-consistent Decoupled Diffusion
by: Lin, Xiaotong, et al.
Published: (2025)

Erased, But Not Forgotten: Erased Rectified Flow Transformers Still Remain Unsafe Under Concept Attack
by: Jiang, Nanxiang, et al.
Published: (2025)

Dual Stream Independence Decoupling for True Emotion Recognition under Masked Expressions
by: Wei, Jinsheng, et al.
Published: (2026)

Modeling Multiple Normal Action Representations for Error Detection in Procedural Tasks
by: Huang, Wei-Jin, et al.
Published: (2025)

Convolutional Prompting for Broad-Domain Retinal Vessel Segmentation
by: Wei, Qijie, et al.
Published: (2024)

Task-Agnostic Guided Feature Expansion for Class-Incremental Learning
by: Zheng, Bowen, et al.
Published: (2025)

ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition
by: Zhou, Jiaming, et al.
Published: (2024)

LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models
by: Fu, Shenghao, et al.
Published: (2025)

Erase to Retain: Low Rank Adaptation Guided Selective Unlearning in Medical Segmentation Networks
by: Datta, Nirjhor, et al.
Published: (2025)

FuseAnyPart: Diffusion-Driven Facial Parts Swapping via Multiple Reference Images
by: Yu, Zheng, et al.
Published: (2024)

Segment Any RGB-Thermal Model with Language-aided Distillation
by: Xing, Dong, et al.
Published: (2025)

Rethinking Decoupled Knowledge Distillation: A Predictive Distribution Perspective
by: Zheng, Bowen, et al.
Published: (2025)

Rethinking Cell Counting Methods: Decoupling Counting and Localization
by: Zheng, Zixuan, et al.
Published: (2025)

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
by: Gu, Yuchao, et al.
Published: (2026)

Rethinking Few-shot Class-incremental Learning: Learning from Yourself
by: Tang, Yu-Ming, et al.
Published: (2024)

PROBE: Diagnosing Residual Concept Capacity in Erased Text-to-Video Diffusion Models
by: Xie, Yiwei, et al.
Published: (2026)

OmniRetriever: Any-to-Any Audio-Video-Text Retrieval via Fusion-as-Teacher Distillation
by: Liu, Yunze, et al.
Published: (2026)

Distilling LLM Prior to Flow Model for Generalizable Agent's Imagination in Object Goal Navigation
by: Li, Badi, et al.
Published: (2025)

Decoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection
by: Inoue, Riku, et al.
Published: (2025)

Erasing Concepts from Text-to-Image Diffusion Models with Few-shot Unlearning
by: Fuchi, Masane, et al.
Published: (2024)

EI: Early Intervention for Multimodal Imaging based Disease Recognition
by: Wei, Qijie, et al.
Published: (2026)

Erasing CLIP Memories: Non-Destructive, Data-Free Zero-Shot class Unlearning in CLIP Models
by: Mishra, Ashish, et al.
Published: (2025)

SAMCT: Segment Any CT Allowing Labor-Free Task-Indicator Prompts
by: Lin, Xian, et al.
Published: (2024)

Task-Decoupled Image Inpainting Framework for Class-specific Object Remover
by: Oh, Changsuk, et al.
Published: (2024)

Designing to Forget: Deep Semi-parametric Models for Unlearning
by: Zheng, Amber Yijia, et al.
Published: (2026)

Scale Decoupled Distillation
by: Luo, Shicai Wei Chunbo Luo Yang
Published: (2024)

Segment Any Class (SAC): Multi-Class Few-Shot Semantic Segmentation via Class Region Proposals
by: Zakir, Hussni Mohd, et al.
Published: (2024)