Modular Embedding Recomposition for Incremental Learning

• URL: http://arxiv.org/abs/2508.16463v2
• Date: Tue, 14 Oct 2025 16:54:27 GMT
• Title: Modular Embedding Recomposition for Incremental Learning
• Authors: Aniello Panariello, Emanuele Frascaroli, Pietro Buzzega, Lorenzo Bonicelli, Angelo Porrello, Simone Calderara,
• Abstract summary: We propose an approach that transforms preservation into enhancement of the zero-shot capabilities of Vision-Language Models (VLMs)<n>Our approach, named MoDular Embedding Recomposition (MoDER), introduces a modular framework that trains multiple textual experts, each specialized in a single seen class, and stores them in a foundational hub.<n>At inference time, for each unseen class, we query the hub and compose the retrieved experts to synthesize a refined prototype that improves classification.
• Score: 23.789486655098585
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The advent of pre-trained Vision-Language Models (VLMs) has significantly transformed Continual Learning (CL), mainly due to their zero-shot classification abilities. Such proficiency makes VLMs well-suited for real-world applications, enabling robust performance on novel unseen classes without requiring adaptation. However, fine-tuning remains essential when downstream tasks deviate significantly from the pre-training domain. Prior CL approaches primarily focus on preserving the zero-shot capabilities of VLMs during incremental fine-tuning on a downstream task. We take a step further by devising an approach that transforms preservation into enhancement of the zero-shot capabilities of VLMs. Our approach, named MoDular Embedding Recomposition (MoDER), introduces a modular framework that trains multiple textual experts, each specialized in a single seen class, and stores them in a foundational hub. At inference time, for each unseen class, we query the hub and compose the retrieved experts to synthesize a refined prototype that improves classification. We show the effectiveness of our method across two popular zero-shot incremental protocols, Class-IL and MTIL, comprising a total of 14 datasets. The codebase is available at https://github.com/aimagelab/mammoth.

Related papers

• Unlocking Prototype Potential: An Efficient Tuning Framework for Few-Shot Class-Incremental Learning [69.28860905525057]
  Few-shot class-incremental learning (FSCIL) seeks to continuously learn new classes from very limited samples.<n>We introduce an efficient prototype fine-tuning framework that evolves static centroids into dynamic, learnable components.
  arXiv  Detail & Related papers  (2026-02-05T03:50:53Z)
• Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting [70.83781268763215]
  Vision-language models (VLMs) have achieved impressive performance across diverse multimodal tasks by leveraging large-scale pre-training.<n>VLMs face unique challenges such as cross-modal feature drift, parameter interference due to shared architectures, and zero-shot capability erosion.<n>This survey aims to serve as a comprehensive and diagnostic reference for researchers developing lifelong vision-language systems.
  arXiv  Detail & Related papers  (2025-08-06T09:03:10Z)
• Beyond CLIP Generalization: Against Forward&Backward Forgetting Adapter for Continual Learning of Vision-Language Models [19.71113926850385]
  The AFA method significantly outperforms existing state-of-the-art approaches.<n>It surpasses the inherent zero-shot performance of CLIP in terms of transferability.
  arXiv  Detail & Related papers  (2025-05-12T15:56:23Z)
• CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning [17.614980614656407]
  We propose Continual Generative training for Incremental prompt-Learning. We exploit Variational Autoencoders to learn class-conditioned distributions. We show that such a generative replay approach can adapt to new tasks while improving zero-shot capabilities.
  arXiv  Detail & Related papers  (2024-07-22T16:51:28Z)
• Enhancing Visual Continual Learning with Language-Guided Supervision [76.38481740848434]
  Continual learning aims to empower models to learn new tasks without forgetting previously acquired knowledge. We argue that the scarce semantic information conveyed by the one-hot labels hampers the effective knowledge transfer across tasks. Specifically, we use PLMs to generate semantic targets for each class, which are frozen and serve as supervision signals.
  arXiv  Detail & Related papers  (2024-03-24T12:41:58Z)
• Read Between the Layers: Leveraging Multi-Layer Representations for Rehearsal-Free Continual Learning with Pre-Trained Models [15.847302755988506]
  We address the Continual Learning problem, wherein a model must learn a sequence of tasks from non-stationary distributions. We propose LayUP, a new prototype-based approach to CL that leverages second-order feature statistics from multiple intermediate layers of a pre-trained network. Our results demonstrate that fully exhausting the representational capacities of pre-trained models in CL goes well beyond their final embeddings.
  arXiv  Detail & Related papers  (2023-12-13T13:11:44Z)
• Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models [55.5610165938949]
  Fine-tuning vision-language models (VLMs) has gained increasing popularity due to its practical value. This paper explores the collaborative potential of leveraging much weaker VLMs to enhance the generalization of a robust single model. We introduce three customized ensemble strategies, each tailored to one specific scenario. The proposed ensemble strategies are evaluated on zero-shot, base-to-new, and cross-dataset generalization, achieving new state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-11-28T05:17:25Z)
• RanPAC: Random Projections and Pre-trained Models for Continual Learning [59.07316955610658]
  Continual learning (CL) aims to learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. We propose a concise and effective approach for CL with pre-trained models.
  arXiv  Detail & Related papers  (2023-07-05T12:49:02Z)
• Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models [13.340759455910721]
  We propose a novel method to prevent zero-shot transfer degradation in the continual learning of vision-language models. Our method outperforms other methods in the traditional class-incremental learning setting.
  arXiv  Detail & Related papers  (2023-03-12T10:28:07Z)
• Task Residual for Tuning Vision-Language Models [69.22958802711017]
  We propose a new efficient tuning approach for vision-language models (VLMs) named Task Residual Tuning (TaskRes) TaskRes explicitly decouples the prior knowledge of the pre-trained models and new knowledge regarding a target task. The proposed TaskRes is simple yet effective, which significantly outperforms previous methods on 11 benchmark datasets.
  arXiv  Detail & Related papers  (2022-11-18T15:09:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.