ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2504.06021
22
0

Memory-Modular Classification: Learning to Generalize with Memory Replacement

8 April 2025
Dahyun Kang
Ahmet Iscen
Eunchan Jo
Sua Choi
Minsu Cho
Cordelia Schmid
    VLM
    KELM
    OffRL
ArXivPDFHTML
Abstract

We propose a novel memory-modular learner for image classification that separates knowledge memorization from reasoning. Our model enables effective generalization to new classes by simply replacing the memory contents, without the need for model retraining. Unlike traditional models that encode both world knowledge and task-specific skills into their weights during training, our model stores knowledge in the external memory of web-crawled image and text data. At inference time, the model dynamically selects relevant content from the memory based on the input image, allowing it to adapt to arbitrary classes by simply replacing the memory contents. The key differentiator that our learner meta-learns to perform classification tasks with noisy web data from unseen classes, resulting in robust performance across various classification scenarios. Experimental results demonstrate the promising performance and versatility of our approach in handling diverse classification tasks, including zero-shot/few-shot classification of unseen classes, fine-grained classification, and class-incremental classification.

View on arXiv
@article{kang2025_2504.06021,
  title={ Memory-Modular Classification: Learning to Generalize with Memory Replacement },
  author={ Dahyun Kang and Ahmet Iscen and Eunchan Jo and Sua Choi and Minsu Cho and Cordelia Schmid },
  journal={arXiv preprint arXiv:2504.06021},
  year={ 2025 }
}
Comments on this paper