Cover Image

A Good Start Matters: Enhancing Continual Learning with Data-Driven Weight Initialization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Harun, Md Yousuf, Kanan, Christopher
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Overcoming the Stability Gap in Continual Learning
by: Harun, Md Yousuf, et al.
Published: (2023)

GRASP: A Rehearsal Policy for Efficient Online Continual Learning
by: Harun, Md Yousuf, et al.
Published: (2023)

Improving Multimodal Large Language Models Using Continual Learning
by: Srivastava, Shikhar, et al.
Published: (2024)

What Variables Affect Out-of-Distribution Generalization in Pretrained Models?
by: Harun, Md Yousuf, et al.
Published: (2024)

Unlocking ImageNet's Multi-Object Nature: Automated Large-Scale Multilabel Annotation
by: Chen, Junyu, et al.
Published: (2026)

Foundation Model Makes Clustering A Better Initialization For Cold-Start Active Learning
by: Yuan, Han, et al.
Published: (2024)

Are Bias Mitigation Techniques for Deep Learning Effective?
by: Shrestha, Robik, et al.
Published: (2021)

Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning
by: Harun, Md Yousuf, et al.
Published: (2025)

On Using Quasirandom Sequences in Machine Learning for Model Weight Initialization
by: Miranskyy, Andriy, et al.
Published: (2024)

Good Data Is All Imitation Learning Needs
by: Samadi, Amir, et al.
Published: (2024)

Self-Supervised Weight Templates for Scalable Vision Model Initialization
by: Xie, Yucheng, et al.
Published: (2026)

Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment
by: Du, Jiawei, et al.
Published: (2024)

Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning
by: Liang, Jinglin, et al.
Published: (2024)

Learning to Weight Parameters for Training Data Attribution
by: Li, Shuangqi, et al.
Published: (2025)

Improving Learning of New Diseases through Knowledge-Enhanced Initialization for Federated Adapter Tuning
by: Peng, Danni, et al.
Published: (2025)

How Weight Resampling and Optimizers Shape the Dynamics of Continual Learning and Forgetting in Neural Networks
by: Frati, Lapo, et al.
Published: (2025)

Continual Learning on a Data Diet
by: Yildirim, Elif Ceren Gok, et al.
Published: (2024)

Adapter-Enhanced Semantic Prompting for Continual Learning
by: Yin, Baocai, et al.
Published: (2024)

Elastic Feature Consolidation for Cold Start Exemplar-Free Incremental Learning
by: Magistri, Simone, et al.
Published: (2024)

Experimental Comparison of Light-Weight and Deep CNN Models Across Diverse Datasets
by: Papon, Md. Hefzul Hossain, et al.
Published: (2026)

Warm Starts Accelerate Conditional Diffusion
by: Scholz, Jonas, et al.
Published: (2025)

Covariance-Aware Goodness for Scalable Forward-Forward Learning
by: Jiang, Xiaoyi, et al.
Published: (2026)

Dealing with Synthetic Data Contamination in Online Continual Learning
by: Wang, Maorong, et al.
Published: (2024)

Advancing Weight and Channel Sparsification with Enhanced Saliency
by: Sun, Xinglong, et al.
Published: (2025)

STAR: Stability-Inducing Weight Perturbation for Continual Learning
by: Eskandar, Masih, et al.
Published: (2025)

Elastic Weight Consolidation Done Right for Continual Learning
by: Liu, Xuan, et al.
Published: (2026)

BloomVQA: Assessing Hierarchical Multi-modal Comprehension
by: Gong, Yunye, et al.
Published: (2023)

Stable Diffusion Models are Secretly Good at Visual In-Context Learning
by: Oorloff, Trevine, et al.
Published: (2025)

WarmFed: Federated Learning with Warm-Start for Globalization and Personalization Via Personalized Diffusion Models
by: Feng, Tao, et al.
Published: (2025)

Divide-and-Conquer for Enhancing Unlabeled Learning, Stability, and Plasticity in Semi-supervised Continual Learning
by: Duan, Yue, et al.
Published: (2025)

Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning
by: He, Lingfeng, et al.
Published: (2026)

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

Continual Learning: Applications and the Road Forward
by: Verwimp, Eli, et al.
Published: (2023)

Segment Anything Model is a Good Teacher for Local Feature Learning
by: Wu, Jingqian, et al.
Published: (2023)

Revitalizing Electoral Trust: Enhancing Transparency and Efficiency through Automated Voter Counting with Machine Learning
by: Faris, Mir, et al.
Published: (2024)

Pruning at Initialization -- A Sketching Perspective
by: Bar, Noga, et al.
Published: (2023)

FedCTTA: A Collaborative Approach to Continual Test-Time Adaptation in Federated Learning
by: Rajib, Rakibul Hasan, et al.
Published: (2025)

Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning
by: Shi, Yujun, et al.
Published: (2021)

Revisiting Transformation Invariant Geometric Deep Learning: An Initial Representation Perspective
by: Zhang, Ziwei, et al.
Published: (2021)

Data-Driven Analysis of Intersectional Bias in Image Classification: A Framework with Bias-Weighted Augmentation
by: Yesmin, Farjana
Published: (2025)