Image de couverture de livre

How green is continual learning, really? Analyzing the energy consumption in continual training of vision foundation models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Trinci, Tomaso, Magistri, Simone, Verdecchia, Roberto, Bagdanov, Andrew D.
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Elastic Feature Consolidation for Cold Start Exemplar-Free Incremental Learning
par: Magistri, Simone, et autres
Publié: (2024)

An Empirical Analysis of Forgetting in Pre-trained Models with Incremental Low-Rank Updates
par: Soutif--Cormerais, Albin, et autres
Publié: (2024)

EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learning
par: Magistri, Simone, et autres
Publié: (2025)

SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery
par: Caselli, Lorenzo, et autres
Publié: (2026)

Preventing Latent Rehearsal Decay in Online Continual SSL with SOLAR
par: Cignoni, Giacomo, et autres
Publié: (2026)

Enhancing Multimodal Large Language Models for Safety-Critical Driving Video Analysis
par: Trinci, Tomaso, et autres
Publié: (2026)

No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces
par: Marczak, Daniel, et autres
Publié: (2025)

Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning
par: Goswami, Dipam, et autres
Publié: (2024)

IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment
par: Magistri, Simone, et autres
Publié: (2026)

Towards stable training of parallel continual learning
par: Yuepan, Li, et autres
Publié: (2024)

Offline Reinforcement Learning with Imputed Rewards
par: Romeo, Carlo, et autres
Publié: (2024)

Machine learning for structural design models of continuous beam systems via influence zones
par: Gallet, Adrien, et autres
Publié: (2024)

ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders
par: Romeo, Carlo, et autres
Publié: (2026)

DICE: Discrete inverse continuity equation for learning population dynamics
par: Blickhan, Tobias, et autres
Publié: (2025)

A Benchmark Environment for Offline Reinforcement Learning in Racing Games
par: Macaluso, Girolamo, et autres
Publié: (2024)

An energy-efficient spiking neural network with continuous learning for self-adaptive brain-machine interface
par: Biyan, Zhou, et autres
Publié: (2025)

Bayesian continual learning and forgetting in neural networks
par: Bonnet, Djohan, et autres
Publié: (2025)

TinySubNets: An efficient and low capacity continual learning strategy
par: Pietroń, Marcin, et autres
Publié: (2024)

Local vs Global continual learning
par: Lanzillotta, Giulia, et autres
Publié: (2024)

A preliminary study on continual learning in computer vision using Kolmogorov-Arnold Networks
par: Cacciatore, Alessandro, et autres
Publié: (2024)

Soup to go: mitigating forgetting during continual learning with model averaging
par: Kleiman, Anat, et autres
Publié: (2025)

Position: Lifetime tuning is incompatible with continual reinforcement learning
par: Mesbahi, Golnaz, et autres
Publié: (2024)

Task agnostic continual learning with Pairwise layer architecture
par: Keskinen, Santtu
Publié: (2024)

Scores as Actions: a framework of fine-tuning diffusion models by continuous-time reinforcement learning
par: Zhao, Hanyang, et autres
Publié: (2024)

Quantum reinforcement learning in continuous action space
par: Wu, Shaojun, et autres
Publié: (2020)

Intrinsic preservation of plasticity in continual quantum learning
par: Chen, Yu-Qin, et autres
Publié: (2025)

Brain-inspired continual pre-trained learner via silent synaptic consolidation
par: Ran, Xuming, et autres
Publié: (2024)

General surgery vision transformer: A video pre-trained foundation model for general surgery
par: Schmidgall, Samuel, et autres
Publié: (2024)

Forager: a lightweight testbed for continual learning with partial observability in RL
par: Tang, Steven, et autres
Publié: (2026)

SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data
par: Romeo, Carlo, et autres
Publié: (2026)

SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learning
par: Romeo, Carlo, et autres
Publié: (2025)

On efficiently computable functions, deep networks and sparse compositionality
par: Poggio, Tomaso
Publié: (2025)

Information Filtering Networks: Theoretical Foundations, Generative Methodologies, and Real-World Applications
par: Aste, Tomaso
Publié: (2025)

Cometh: A continuous-time discrete-state graph diffusion model
par: Siraudin, Antoine, et autres
Publié: (2024)

A foundation model of vision, audition, and language for in-silico neuroscience
par: d'Ascoli, Stéphane, et autres
Publié: (2026)

Analytical results for uncertainty propagation through trained machine learning regression models
par: Thompson, Andrew
Publié: (2024)

A multifidelity approach to continual learning for physical systems
par: Howard, Amanda, et autres
Publié: (2023)

Bias correction of wind power forecasts with SCADA data and continuous learning
par: Jonas, Stefan, et autres
Publié: (2024)

Unlearning-based sliding window for continual learning under concept drift
par: Wozniak, Michal, et autres
Publié: (2026)

Inter-environmental world modeling for continuous and compositional dynamics
par: Hayashi, Kohei, et autres
Publié: (2025)