Imagen de Portada

An Empirical Analysis of Forgetting in Pre-trained Models with Incremental Low-Rank Updates

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Soutif--Cormerais, Albin, Magistri, Simone, van de Weijer, Joost, Bagdanov, Andew D.
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learning
por: Magistri, Simone, et al.
Publicado: (2025)

The Expanding Scope of the Stability Gap: Unveiling its Presence in Joint Incremental Learning of Homogeneous Tasks
por: Kamath, Sandesh, et al.
Publicado: (2024)

On the importance of cross-task features for class-incremental learning
por: Soutif--Cormerais, Albin, et al.
Publicado: (2021)

No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces
por: Marczak, Daniel, et al.
Publicado: (2025)

Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning
por: Goswami, Dipam, et al.
Publicado: (2024)

IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment
por: Magistri, Simone, et al.
Publicado: (2026)

How green is continual learning, really? Analyzing the energy consumption in continual training of vision foundation models
por: Trinci, Tomaso, et al.
Publicado: (2024)

Accurate and Efficient Low-Rank Model Merging in Core Space
por: Panariello, Aniello, et al.
Publicado: (2025)

Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning
por: Goswami, Dipam, et al.
Publicado: (2024)

SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery
por: Caselli, Lorenzo, et al.
Publicado: (2026)

Preventing Latent Rehearsal Decay in Online Continual SSL with SOLAR
por: Cignoni, Giacomo, et al.
Publicado: (2026)

Routing without Forgetting
por: Masano, Alessio, et al.
Publicado: (2026)

Revisiting Weight Regularization for Low-Rank Continual Learning
por: Zheng, Yaoyue, et al.
Publicado: (2026)

Assessing Open-world Forgetting in Generative Image Model Customization
por: Laria, Héctor, et al.
Publicado: (2024)

Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers
por: Goswami, Dipam, et al.
Publicado: (2024)

Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models
por: Goswami, Dipam, et al.
Publicado: (2025)

Mitigating Forgetting in Low Rank Adaptation
por: Sliwa, Joanna, et al.
Publicado: (2025)

Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting
por: Liu, Yuyang, et al.
Publicado: (2025)

InRank: Incremental Low-Rank Learning
por: Zhao, Jiawei, et al.
Publicado: (2023)

C-LoRA: Continual Low-Rank Adaptation for Pre-trained Models
por: Zhang, Xin, et al.
Publicado: (2025)

An Efficient Replay for Class-Incremental Learning with Pre-trained Models
por: Yin, Weimin, et al.
Publicado: (2024)

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

Cross-Modal Prototype Alignment and Mixing for Training-Free Few-Shot Classification
por: Goswami, Dipam, et al.
Publicado: (2026)

FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
por: Goswami, Dipam, et al.
Publicado: (2023)

Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptation
por: Gu, Hao, et al.
Publicado: (2026)

SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learning
por: Romeo, Carlo, et al.
Publicado: (2025)

Learn or Recall? Revisiting Incremental Learning with Pre-trained Language Models
por: Zheng, Junhao, et al.
Publicado: (2023)

PreLoRA: Hybrid Pre-training of Vision Transformers with Full Training and Low-Rank Adapters
por: Thapa, Krishu K, et al.
Publicado: (2025)

Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation
por: Li, Yi-Chen, et al.
Publicado: (2024)

TROFI: Trajectory-Ranked Offline Inverse Reinforcement Learning
por: Sestini, Alessandro, et al.
Publicado: (2025)

Delayed Bottlenecking: Alleviating Forgetting in Pre-trained Graph Neural Networks
por: Zhao, Zhe, et al.
Publicado: (2024)

Low-Rank Adaptation Reduces Catastrophic Forgetting in Sequential Transformer Encoder Fine-Tuning: Controlled Empirical Evidence and Frozen-Backbone Representation Probes
por: Pandey, Ashish
Publicado: (2026)

On Catastrophic Forgetting in Low-Rank Decomposition-Based Parameter-Efficient Fine-Tuning
por: Ahmad, Muhammad, et al.
Publicado: (2026)

Offline Reinforcement Learning with Imputed Rewards
por: Romeo, Carlo, et al.
Publicado: (2024)

Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers
por: Szatkowski, Filip, et al.
Publicado: (2024)

CLA: Latent Alignment for Online Continual Self-Supervised Learning
por: Cignoni, Giacomo, et al.
Publicado: (2025)

ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders
por: Romeo, Carlo, et al.
Publicado: (2026)

An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration
por: Naganuma, Hiroki, et al.
Publicado: (2023)

LOST: Low-rank and Sparse Pre-training for Large Language Models
por: Li, Jiaxi, et al.
Publicado: (2025)