Image de couverture de livre

Take Only What You Need: Rank Minimization as an Implicit Forgetting Regularizer in Continual Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lu, Haodong, Zhao, Chongyang, Xue, Jason, Yao, Lina, Moore, Kristen, Gong, Dong
Format:	Preprint
Publié:	2024
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

Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts
par: Lu, Haodong, et autres
Publié: (2025)

Learning with Mixture of Prototypes for Out-of-Distribution Detection
par: Lu, Haodong, et autres
Publié: (2024)

Continual Learning on CLIP via Incremental Prompt Tuning with Intrinsic Textual Anchors
par: Lu, Haodong, et autres
Publié: (2025)

Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning
par: Wang, Huiyi, et autres
Publié: (2024)

On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models
par: Zhao, Chongyang, et autres
Publié: (2026)

CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models
par: Jha, Saurav, et autres
Publié: (2024)

AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation
par: Wang, Zhengren, et autres
Publié: (2026)

Take What You Need: Flexible Multi-Task Semantic Communications with Channel Adaptation
par: Chen, Xiang, et autres
Publié: (2025)

Learning Mamba as a Continual Learner: Meta-learning Selective State Space Models for Efficient Continual Learning
par: Zhao, Chongyang, et autres
Publié: (2024)

Continual Learning for Remote Physiological Measurement: Minimize Forgetting and Simplify Inference
par: Liang, Qian, et autres
Publié: (2024)

Perceptual Inductive Bias Is What You Need Before Contrastive Learning
par: Li, Tianqin, et autres
Publié: (2025)

You Only Need Less Attention at Each Stage in Vision Transformers
par: Zhang, Shuoxi, et autres
Publié: (2024)

Smart Feature is What You Need
par: Hu, Zhaoxin, et autres
Publié: (2024)

You Only Speak Once to See
par: Yang, Wenhao, et autres
Publié: (2024)

You Only Need Half: Boosting Data Augmentation by Using Partial Content
par: Hu, Juntao, et autres
Publié: (2024)

You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement
par: Yan, Qingsen, et autres
Publié: (2024)

You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
par: Wei, Zhepei, et autres
Publié: (2026)

Forget Less, Retain More: A Lightweight Regularizer for Rehearsal-Based Continual Learning
par: Alssum, Lama, et autres
Publié: (2025)

Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling
par: Shao, Shitong, et autres
Publié: (2023)

OMGSR: You Only Need One Mid-timestep Guidance for Real-World Image Super-Resolution
par: Wu, Zhiqiang, et autres
Publié: (2025)

Learn to Memorize and to Forget: A Continual Learning Perspective of Dynamic SLAM
par: Li, Baicheng, et autres
Publié: (2024)

Beyond CLIP Generalization: Against Forward&Backward Forgetting Adapter for Continual Learning of Vision-Language Models
par: Dong, Songlin, et autres
Publié: (2025)

Chameleon: Images Are What You Need For Multimodal Learning Robust To Missing Modalities
par: Liaqat, Muhammad Irzam, et autres
Publié: (2024)

SeTformer is What You Need for Vision and Language
par: Shamsolmoali, Pourya, et autres
Publié: (2024)

YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting
par: Ye, Botao, et autres
Publié: (2025)

You Need a Transition Plane: Bridging Continuous Panoramic 3D Reconstruction with Perspective Gaussian Splatting
par: Shen, Zhijie, et autres
Publié: (2025)

SMFD-UNet: Semantic Face Mask Is The Only Thing You Need To Deblur Faces
par: Zami, Abduz
Publié: (2026)

IMEX-Reg: Implicit-Explicit Regularization in the Function Space for Continual Learning
par: Bhat, Prashant, et autres
Publié: (2024)

Learning to See What You Need: Gaze Attention for Multimodal Large Language Models
par: Song, Junha, et autres
Publié: (2026)

You Only Need One Step: Fast Super-Resolution with Stable Diffusion via Scale Distillation
par: Noroozi, Mehdi, et autres
Publié: (2024)

You Only Need Two Detectors to Achieve Multi-Modal 3D Multi-Object Tracking
par: Wang, Xiyang, et autres
Publié: (2023)

Only Send What You Need: Learning to Communicate Efficiently in Federated Multilingual Machine Translation
par: Chu, Yun-Wei, et autres
Publié: (2024)

Forward-Only Continual Learning
par: Chen, Jiao, et autres
Publié: (2025)

You Only Train Once
par: Sakaridis, Christos
Publié: (2025)

Continual Learning and Catastrophic Forgetting
par: van de Ven, Gido M., et autres
Publié: (2024)

Choose What You Need: Disentangled Representation Learning for Scene Text Recognition, Removal and Editing
par: Zhang, Boqiang, et autres
Publié: (2024)

Masked Generative Transformer Is What You Need for Image Editing
par: Chow, Wei, et autres
Publié: (2026)

Lite-SAM Is Actually What You Need for Segment Everything
par: Fu, Jianhai, et autres
Publié: (2024)

SPARNet: Continual Test-Time Adaptation via Sample Partitioning Strategy and Anti-Forgetting Regularization
par: Meng, Xinru, et autres
Publié: (2025)

Slowing Down Forgetting in Continual Learning
par: Janetzky, Pascal, et autres
Publié: (2024)