13 papers
Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision Models
Sergi Masip, Alicja Dobrzeniecka, Jonathan Swinnen +4
Traditionally, continual learning has assumed access to labeled data, yet many real-world applications -- such as lifelong robotics -- require models to adapt continuously from unl…
Beyond Classification: Dynamic Adapter Routing for Continual Multimodal Retrieval
Alicja Dobrzeniecka, Filip Szatkowski, Sebastian Cygert +2
While retrieval is a core function of vision-language models, continually updating these models for retrieval tasks remains critically underexplored. Existing work often approaches…
IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment
Simone Magistri, Dipam Goswami, Marco Mistretta +3
Vision-Language Models like CLIP are extensively used for inter-modal tasks which involve both visual and text modalities. However, when the individual modality encoders are applie…
Online Continual Learning with Dynamic Label Hierarchies
Xinrui Wang, Shao-Yuan Li, BartÅomiej Twardowski +2
Online Continual Learning (OCL) aims to learn from endless non\text{-}stationary data streams, yet most existing methods assume a flat label space and overlook the hierarchical org…
Cross-Modal Prototype Alignment and Mixing for Training-Free Few-Shot Classification
Dipam Goswami, Simone Magistri, Gido M. van de Ven +4
Vision-language models (VLMs) like CLIP are trained with the objective of aligning text and image pairs. To improve CLIP-based few-shot image classification, recent works have obse…
Accurate and Efficient Low-Rank Model Merging in Core Space
Aniello Panariello, Daniel Marczak, Simone Magistri +5
In this paper, we address the challenges associated with merging low-rank adaptations of large neural networks. With the rise of parameter-efficient adaptation techniques, such as…