Image de couverture de livre

LetheViT: Selective Machine Unlearning for Vision Transformers via Attention-Guided Contrastive Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Tong, Yujia, Zhang, Tian, Yuan, Jingling, Wang, Yuze, Hu, Chuang
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Enhancing Quantization-Aware Training on Edge Devices via Relative Entropy Coreset Selection and Cascaded Layer Correction
par: Tong, Yujia, et autres
Publié: (2025)

DFQ-ViT: Data-Free Quantization for Vision Transformers without Fine-tuning
par: Tong, Yujia, et autres
Publié: (2025)

SAGE: Accelerating Vision-Language Models via Entropy-Guided Adaptive Speculative Decoding
par: Tong, Yujia, et autres
Publié: (2026)

Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels
par: Tong, Yujia, et autres
Publié: (2025)

ViT-MUL: A Baseline Study on Recent Machine Unlearning Methods Applied to Vision Transformers
par: Cho, Ikhyun, et autres
Publié: (2024)

Visual Attention Drifts,but Anchors Hold:Mitigating Hallucination in Multimodal Large Language Models via Cross-Layer Visual Anchors
par: Yang, Chengxu, et autres
Publié: (2026)

WriteViT: Handwritten Text Generation with Vision Transformer
par: Nam, Dang Hoai, et autres
Publié: (2025)

FasterViT: Fast Vision Transformers with Hierarchical Attention
par: Hatamizadeh, Ali, et autres
Publié: (2023)

CoUn: Empowering Machine Unlearning via Contrastive Learning
par: Khalil, Yasser H., et autres
Publié: (2025)

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers
par: Sinha, Sanchit, et autres
Publié: (2025)

Federated EndoViT: Pretraining Vision Transformers via Federated Learning on Endoscopic Image Collections
par: Kirchner, Max, et autres
Publié: (2025)

ViTCN: Vision Transformer Contrastive Network For Reasoning
par: Song, Bo, et autres
Publié: (2024)

MuViT: Multi-Resolution Vision Transformers for Learning Across Scales in Microscopy
par: Mantes, Albert Dominguez, et autres
Publié: (2026)

Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning
par: Zhang, Jihai, et autres
Publié: (2024)

Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning
par: Patel, Gaurav, et autres
Publié: (2025)

UniRefiner: Teaching Pre-trained ViTs to Self-Dispose Dross via Contrastive Register
par: Qiu, Congpei, et autres
Publié: (2026)

ViT-AdaLA: Adapting Vision Transformers with Linear Attention
par: Li, Yifan, et autres
Publié: (2026)

Cross-Modal Attention Guided Unlearning in Vision-Language Models
par: Bhaila, Karuna, et autres
Publié: (2025)

Attention Transfer Is Not Universally Effective for Vision Transformers
par: Qin, Huaiyuan, et autres
Publié: (2026)

VersaViT: Enhancing MLLM Vision Backbones via Task-Guided Optimization
par: Liu, Yikun, et autres
Publié: (2026)

Erase at the Core: Representation Unlearning for Machine Unlearning
par: Lee, Jaewon, et autres
Publié: (2026)

Learning to Unlearn for Robust Machine Unlearning
par: Huang, Mark He, et autres
Publié: (2024)

Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference
par: You, Haoran, et autres
Publié: (2022)

GeoViSTA: Geospatial Vision-Tabular Transformer for Multimodal Environment Representation
par: Liu, Yuhao, et autres
Publié: (2026)

LL-ViT: Edge Deployable Vision Transformers with Look Up Table Neurons
par: Nag, Shashank, et autres
Publié: (2025)

FairViT: Fair Vision Transformer via Adaptive Masking
par: Tian, Bowei, et autres
Publié: (2024)

Ultrasound Vision-Language Alignment via Contrastive Learning
par: Lyu, Zhuoyang, et autres
Publié: (2026)

ViTGAN: Training GANs with Vision Transformers
par: Lee, Kwonjoon, et autres
Publié: (2021)

Using Interleaved Ensemble Unlearning to Keep Backdoors at Bay for Finetuning Vision Transformers
par: Li, Zeyu Michael
Publié: (2024)

ViViDex: Learning Vision-based Dexterous Manipulation from Human Videos
par: Chen, Zerui, et autres
Publié: (2024)

Learning Visual Prompts for Guiding the Attention of Vision Transformers
par: Rezaei, Razieh, et autres
Publié: (2024)

Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking
par: Deng, Kaiyuan, et autres
Publié: (2026)

ViTNT-FIQA: Training-Free Face Image Quality Assessment with Vision Transformers
par: Ozgur, Guray, et autres
Publié: (2026)

EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction
par: Cai, Han, et autres
Publié: (2022)

Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning
par: Chen, Shiming, et autres
Publié: (2024)

GNN-ViTCap: GNN-Enhanced Multiple Instance Learning with Vision Transformers for Whole Slide Image Classification and Captioning
par: Raju, S M Taslim Uddin, et autres
Publié: (2025)

Multi-Domain Features Guided Supervised Contrastive Learning for Radar Target Detection
par: Wang, Junjie, et autres
Publié: (2024)

DAGLFNet: Deep Feature Attention Guided Global and Local Feature Fusion for Pseudo-Image Point Cloud Segmentation
par: Chen, Chuang, et autres
Publié: (2025)

VariViT: A Vision Transformer for Variable Image Sizes
par: Varma, Aswathi, et autres
Publié: (2026)

ScriptViT: Vision Transformer-Based Personalized Handwriting Generation
par: Acharya, Sajjan, et autres
Publié: (2025)