Continual Cross-Modal Generalization

• URL: http://arxiv.org/abs/2504.00561v1
• Date: Tue, 01 Apr 2025 09:16:20 GMT
• Title: Continual Cross-Modal Generalization
• Authors: Yan Xia, Hai Huang, Minghui Fang, Zhou Zhao,
• Abstract summary: Cross-modal generalization aims to learn a shared representation space from multimodal pairs.<n>We propose a continual learning approach that incrementally maps new modalities into a shared codebook via a mediator modality.<n>Experiments on image-text, audio-text, video-text, and speech-text show that our method achieves strong performance on various cross-modal generalization tasks.
• Score: 48.56694158680082
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cross-modal generalization aims to learn a shared discrete representation space from multimodal pairs, enabling knowledge transfer across unannotated modalities. However, achieving a unified representation for all modality pairs requires extensive paired data, which is often impractical. Inspired by the availability of abundant bimodal data (e.g., in ImageBind), we explore a continual learning approach that incrementally maps new modalities into a shared discrete codebook via a mediator modality. We propose the Continual Mixture of Experts Adapter (CMoE-Adapter) to project diverse modalities into a unified space while preserving prior knowledge. To align semantics across stages, we introduce a Pseudo-Modality Replay (PMR) mechanism with a dynamically expanding codebook, enabling the model to adaptively incorporate new modalities using learned ones as guidance. Extensive experiments on image-text, audio-text, video-text, and speech-text show that our method achieves strong performance on various cross-modal generalization tasks. Code is provided in the supplementary material.

Related papers

• Towards Modality Generalization: A Benchmark and Prospective Analysis [56.84045461854789]
  This paper introduces Modality Generalization (MG), which focuses on enabling models to generalize to unseen modalities. We propose a comprehensive benchmark featuring multi-modal algorithms and adapt existing methods that focus on generalization. Our work provides a foundation for advancing robust and adaptable multi-modal models, enabling them to handle unseen modalities in realistic scenarios.
  arXiv  Detail & Related papers  (2024-12-24T08:38:35Z)
• Alt-MoE:A Scalable Framework for Bidirectional Multimodal Alignment and Efficient Knowledge Integration [6.928469290518152]
  Multimodal learning has advanced significantly by aligning different modalities within shared latent spaces.<n>Direct alignment struggles to fully leverage rich intra-modal knowledge, often requiring extensive training data to achieve cross-modal representation.<n>We introduce Alt-MoE, a scalable multimodal alignment framework that employs a mixture of experts (MoE) model as a multi-directional connector across modalities.
  arXiv  Detail & Related papers  (2024-09-09T10:40:50Z)
• Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities [8.517830626176641]
  Any2Seg is a novel framework that can achieve robust segmentation from any combination of modalities in any visual conditions. Experiments on two benchmarks with four modalities demonstrate that Any2Seg achieves the state-of-the-art under the multi-modal setting.
  arXiv  Detail & Related papers  (2024-07-16T03:34:38Z)
• Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding [62.70450216120704]
  Unsupervised pre-training has shown great success in skeleton-based action understanding. We propose a Unified Multimodal Unsupervised Representation Learning framework, called UmURL. UmURL exploits an efficient early-fusion strategy to jointly encode the multi-modal features in a single-stream manner.
  arXiv  Detail & Related papers  (2023-11-06T13:56:57Z)
• Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Grounding [54.49214267905562]
  We construct a transformer-based framework for multi-modal manipulation detection and grounding tasks. Our framework simultaneously explores modality-specific features while preserving the capability for multi-modal alignment. We propose an implicit manipulation query (IMQ) that adaptively aggregates global contextual cues within each modality.
  arXiv  Detail & Related papers  (2023-09-22T06:55:41Z)
• One-stage Modality Distillation for Incomplete Multimodal Learning [7.791488931628906]
  This paper presents a one-stage modality distillation framework that unifies the privileged knowledge transfer and modality information fusion. The proposed framework can overcome the problem of incomplete modality input in various scenes and achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-09-15T07:12:27Z)
• Decoupling Common and Unique Representations for Multimodal Self-supervised Learning [22.12729786091061]
  We propose Decoupling Common and Unique Representations (DeCUR), a simple yet effective method for multimodal self-supervised learning. By distinguishing inter- and intra-modal embeddings through multimodal redundancy reduction, DeCUR can integrate complementary information across different modalities.
  arXiv  Detail & Related papers  (2023-09-11T08:35:23Z)
• Preserving Modality Structure Improves Multi-Modal Learning [64.10085674834252]
  Self-supervised learning on large-scale multi-modal datasets allows learning semantically meaningful embeddings without relying on human annotations. These methods often struggle to generalize well on out-of-domain data as they ignore the semantic structure present in modality-specific embeddings. We propose a novel Semantic-Structure-Preserving Consistency approach to improve generalizability by preserving the modality-specific relationships in the joint embedding space.
  arXiv  Detail & Related papers  (2023-08-24T20:46:48Z)
• Learning Unseen Modality Interaction [54.23533023883659]
  Multimodal learning assumes all modality combinations of interest are available during training to learn cross-modal correspondences. We pose the problem of unseen modality interaction and introduce a first solution. It exploits a module that projects the multidimensional features of different modalities into a common space with rich information preserved.
  arXiv  Detail & Related papers  (2023-06-22T10:53:10Z)

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.