Image de couverture de livre

Cross-Modal Prototype Alignment and Mixing for Training-Free Few-Shot Classification

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Goswami, Dipam, Magistri, Simone, van de Ven, Gido M., Twardowski, Bartłomiej, Bagdanov, Andrew D., Tuytelaars, Tinne, van de Weijer, Joost
Format:	Preprint
Publié:	2026
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

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

Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers
par: Goswami, Dipam, et autres
Publié: (2024)

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

FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
par: Goswami, Dipam, et autres
Publié: (2023)

Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models
par: Goswami, Dipam, et autres
Publié: (2025)

Exemplar-free Continual Representation Learning via Learnable Drift Compensation
par: Gomez-Villa, Alex, et autres
Publié: (2024)

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

Prediction Error-based Classification for Class-Incremental Learning
par: Zając, Michał, et autres
Publié: (2023)

Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning
par: Goswami, Dipam, et autres
Publié: (2024)

Forgetting of task-specific knowledge in model merging-based continual learning
par: Hess, Timm, et autres
Publié: (2025)

Two Complementary Perspectives to Continual Learning: Ask Not Only What to Optimize, But Also How
par: Hess, Timm, et autres
Publié: (2023)

Accurate and Efficient Low-Rank Model Merging in Core Space
par: Panariello, Aniello, et autres
Publié: (2025)

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

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)

Putting a Face to Forgetting: Continual Learning meets Mechanistic Interpretability
par: Masip, Sergi, et autres
Publié: (2026)

Knowledge Accumulation in Continually Learned Representations and the Issue of Feature Forgetting
par: Hess, Timm, et autres
Publié: (2023)

Continual Learning of Diffusion Models with Generative Distillation
par: Masip, Sergi, et autres
Publié: (2023)

Addressing The Devastating Effects Of Single-Task Data Poisoning In Exemplar-Free Continual Learning
par: Pawlak, Stanisław, et autres
Publié: (2025)

Exploiting the Semantic Knowledge of Pre-trained Text-Encoders for Continual Learning
par: Yu, Lu, et autres
Publié: (2024)

On the importance of cross-task features for class-incremental learning
par: Soutif--Cormerais, Albin, et autres
Publié: (2021)

Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization
par: Dziadzio, Sebastian, et autres
Publié: (2023)

On the Computation of the Fisher Information in Continual Learning
par: van de Ven, Gido M.
Publié: (2025)

Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers
par: Szatkowski, Filip, et autres
Publié: (2024)

Revisiting Weight Regularization for Low-Rank Continual Learning
par: Zheng, Yaoyue, et autres
Publié: (2026)

PEO: Training-Free Aesthetic Quality Enhancement in Pre-Trained Text-to-Image Diffusion Models with Prompt Embedding Optimization
par: Margaryan, Hovhannes, et autres
Publié: (2025)

Remembering by Reconstructing: Domain Incremental Learning With Test-Time Training on Video Streams
par: Swinnen, Jonathan, et autres
Publié: (2026)

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

Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting
par: Liu, Yuyang, et autres
Publié: (2025)

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

The Art of Deception: Color Visual Illusions and Diffusion Models
par: Gomez-Villa, Alex, et autres
Publié: (2024)

Predicting the Susceptibility of Examples to Catastrophic Forgetting
par: Hacohen, Guy, et autres
Publié: (2024)

Implicit Gaussian Splatting with Efficient Multi-Level Tri-Plane Representation
par: Wu, Minye, et autres
Publié: (2024)

Analysis of Spatial augmentation in Self-supervised models in the purview of training and test distributions
par: Jha, Abhishek, et autres
Publié: (2024)

Distributional value gradients for stochastic environments
par: Debes, Baptiste, et autres
Publié: (2026)

Multivariate Distributional Reinforcement Learning Using Sliced Divergences
par: Debes, Baptiste, et autres
Publié: (2026)

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

How green is continual learning, really? Analyzing the energy consumption in continual training of vision foundation models
par: Trinci, Tomaso, et autres
Publié: (2024)

Routing without Forgetting
par: Masano, Alessio, et autres
Publié: (2026)

TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models
par: Qu, Tingyu, et autres
Publié: (2024)