Exemplar Masking for Multimodal Incremental Learning

• URL: http://arxiv.org/abs/2412.09549v1
• Date: Thu, 12 Dec 2024 18:40:20 GMT
• Title: Exemplar Masking for Multimodal Incremental Learning
• Authors: Yi-Lun Lee, Chen-Yu Lee, Wei-Chen Chiu, Yi-Hsuan Tsai,
• Abstract summary: Multimodal incremental learning needs to digest the information from multiple modalities while concurrently learning new knowledge. In this paper, we propose the exemplar masking framework to efficiently replay old knowledge. We show that our exemplar masking framework is more efficient and robust to catastrophic forgetting under the same limited memory buffer.
• Score: 47.18796033633918
• License:
• Abstract: Multimodal incremental learning needs to digest the information from multiple modalities while concurrently learning new knowledge without forgetting the previously learned information. There are numerous challenges for this task, mainly including the larger storage size of multimodal data in exemplar-based methods and the computational requirement of finetuning on huge multimodal models. In this paper, we leverage the parameter-efficient tuning scheme to reduce the burden of fine-tuning and propose the exemplar masking framework to efficiently replay old knowledge. Specifically, the non-important tokens are masked based on the attention weights and the correlation across different modalities, significantly reducing the storage size of an exemplar and consequently saving more exemplars under the same memory buffer. Moreover, we design a multimodal data augmentation technique to diversify exemplars for replaying prior knowledge. In experiments, we not only evaluate our method in existing multimodal datasets but also extend the ImageNet-R dataset to a multimodal dataset as a real-world application, where captions are generated by querying multimodal large language models (e.g., InstructBLIP). Extensive experiments show that our exemplar masking framework is more efficient and robust to catastrophic forgetting under the same limited memory buffer. Code is available at https://github.com/YiLunLee/Exemplar_Masking_MCIL.

Related papers

• Towards Text-Image Interleaved Retrieval [49.96332254241075]
  We introduce the text-image interleaved retrieval (TIIR) task, where the query and document are interleaved text-image sequences. We construct a TIIR benchmark based on naturally interleaved wikiHow tutorials, where a specific pipeline is designed to generate interleaved queries. We propose a novel Matryoshka Multimodal Embedder (MME), which compresses the number of visual tokens at different granularity.
  arXiv  Detail & Related papers  (2025-02-18T12:00:47Z)
• MambaPro: Multi-Modal Object Re-Identification with Mamba Aggregation and Synergistic Prompt [60.10555128510744]
  Multi-modal object Re-IDentification (ReID) aims to retrieve specific objects by utilizing complementary image information from different modalities. Recently, large-scale pre-trained models like CLIP have demonstrated impressive performance in traditional single-modal object ReID tasks. We introduce a novel framework called MambaPro for multi-modal object ReID.
  arXiv  Detail & Related papers  (2024-12-14T06:33:53Z)
• Train Once, Deploy Anywhere: Matryoshka Representation Learning for Multimodal Recommendation [27.243116376164906]
  We introduce a lightweight framework called full-scale Matryoshka representation learning for multimodal recommendation (fMRLRec) Our fMRLRec captures item features at different granularities, learning informative representations for efficient recommendation across multiple dimensions. We demonstrate the effectiveness and efficiency of fMRLRec on multiple benchmark datasets.
  arXiv  Detail & Related papers  (2024-09-25T05:12:07Z)
• Multi-modal Semantic Understanding with Contrastive Cross-modal Feature Alignment [11.897888221717245]
  This paper proposes a novel CLIP-guided contrastive-learning-based architecture to perform multi-modal feature alignment. Our model is simple to implement without using task-specific external knowledge, and thus can easily migrate to other multi-modal tasks.
  arXiv  Detail & Related papers  (2024-03-11T01:07:36Z)
• Efficient Multimodal Diffusion Models Using Joint Data Infilling with Partially Shared U-Net [20.437172251393257]
  Partially Shared U-Net (PS-U-Net) is an efficient multimodal diffusion model that allows text and image inputs to pass through dedicated layers and skip-connections for preserving modality-specific fine-grained details. Inspired by image inpainting, we also propose a new efficient multimodal sampling method that introduces new scenarios for conditional generation while only requiring a simple joint distribution to be learned. Our empirical exploration of the MS-COCO dataset demonstrates that our method generates multimodal text and image data with higher quality compared to existing multimodal diffusion models.
  arXiv  Detail & Related papers  (2023-11-28T04:34:44Z)
• Efficient Multimodal Fusion via Interactive Prompting [62.08292938484994]
  Large-scale pre-training has brought unimodal fields such as computer vision and natural language processing to a new era. We propose an efficient and flexible multimodal fusion method, namely PMF, tailored for fusing unimodally pre-trained transformers.
  arXiv  Detail & Related papers  (2023-04-13T07:31:51Z)
• Learning Multimodal Data Augmentation in Feature Space [65.54623807628536]
  LeMDA is an easy-to-use method that automatically learns to jointly augment multimodal data in feature space. We show that LeMDA can profoundly improve the performance of multimodal deep learning architectures.
  arXiv  Detail & Related papers  (2022-12-29T20:39:36Z)
• Routing with Self-Attention for Multimodal Capsule Networks [108.85007719132618]
  We present a new multimodal capsule network that allows us to leverage the strength of capsules in the context of a multimodal learning framework. To adapt the capsules to large-scale input data, we propose a novel routing by self-attention mechanism that selects relevant capsules. This allows not only for robust training with noisy video data, but also to scale up the size of the capsule network compared to traditional routing methods.
  arXiv  Detail & Related papers  (2021-12-01T19:01:26Z)
• METEOR: Learning Memory and Time Efficient Representations from Multi-modal Data Streams [19.22829945777267]
  We present METEOR, a novel MEmory and Time Efficient Online Representation learning technique. We show that METEOR preserves the quality of the representations while reducing memory usage by around 80% compared to the conventional memory-intensive embeddings.
  arXiv  Detail & Related papers  (2020-07-23T08:18:02Z)

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.