Detached and Interactive Multimodal Learning

• URL: http://arxiv.org/abs/2407.19514v1
• Date: Sun, 28 Jul 2024 15:38:58 GMT
• Title: Detached and Interactive Multimodal Learning
• Authors: Yunfeng Fan, Wenchao Xu, Haozhao Wang, Junhong Liu, Song Guo,
• Abstract summary: This paper introduces DI-MML, a novel detached MML framework designed to learn complementary information across modalities. It addresses competition by separately training each modality encoder with isolated learning objectives. Experiments conducted on audio-visual, flow-image, and front-rear view datasets show the superior performance of our proposed method.
• Score: 17.843121072628477
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, Multimodal Learning (MML) has gained significant interest as it compensates for single-modality limitations through comprehensive complementary information within multimodal data. However, traditional MML methods generally use the joint learning framework with a uniform learning objective that can lead to the modality competition issue, where feedback predominantly comes from certain modalities, limiting the full potential of others. In response to this challenge, this paper introduces DI-MML, a novel detached MML framework designed to learn complementary information across modalities under the premise of avoiding modality competition. Specifically, DI-MML addresses competition by separately training each modality encoder with isolated learning objectives. It further encourages cross-modal interaction via a shared classifier that defines a common feature space and employing a dimension-decoupled unidirectional contrastive (DUC) loss to facilitate modality-level knowledge transfer. Additionally, to account for varying reliability in sample pairs, we devise a certainty-aware logit weighting strategy to effectively leverage complementary information at the instance level during inference. Extensive experiments conducted on audio-visual, flow-image, and front-rear view datasets show the superior performance of our proposed method. The code is released at https://github.com/fanyunfeng-bit/DI-MML.

Related papers

• LLMs Can Evolve Continually on Modality for X-Modal Reasoning [62.2874638875554]
  Existing methods rely heavily on modal-specific pretraining and joint-modal tuning, leading to significant computational burdens when expanding to new modalities. We propose PathWeave, a flexible and scalable framework with modal-Path sWitching and ExpAnsion abilities. PathWeave performs comparably to state-of-the-art MLLMs while concurrently reducing parameter training burdens by 98.73%.
  arXiv  Detail & Related papers  (2024-10-26T13:19:57Z)
• Harnessing Shared Relations via Multimodal Mixup Contrastive Learning for Multimodal Classification [3.6616868775630587]
  We propose M3CoL, a Multimodal Mixup Contrastive Learning approach to capture nuanced shared relations inherent in multimodal data. Our work highlights the significance of learning shared relations for robust multimodal learning, opening up promising avenues for future research.
  arXiv  Detail & Related papers  (2024-09-26T12:15:13Z)
• What to align in multimodal contrastive learning? [7.7439394183358745]
  We introduce Contrastive MultiModal learning strategy that enables the communication between modalities in a single multimodal space. Our theoretical analysis shows that shared, synergistic and unique terms of information naturally emerge from this formulation, allowing us to estimate multimodal interactions beyond redundancy. In the latter, CoMM learns complex multimodal interactions and achieves state-of-the-art results on the six multimodal benchmarks.
  arXiv  Detail & Related papers  (2024-09-11T16:42:22Z)
• Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts [54.529880848937104]
  We develop a unified MLLM with the MoE architecture, named Uni-MoE, that can handle a wide array of modalities. Specifically, it features modality-specific encoders with connectors for a unified multimodal representation. We evaluate the instruction-tuned Uni-MoE on a comprehensive set of multimodal datasets.
  arXiv  Detail & Related papers  (2024-05-18T12:16:01Z)
• Balanced Multi-modal Federated Learning via Cross-Modal Infiltration [19.513099949266156]
  Federated learning (FL) underpins advancements in privacy-preserving distributed computing. We propose a novel Cross-Modal Infiltration Federated Learning (FedCMI) framework.
  arXiv  Detail & Related papers  (2023-12-31T05:50:15Z)
• Multimodal Representation Learning by Alternating Unimodal Adaptation [73.15829571740866]
  We propose MLA (Multimodal Learning with Alternating Unimodal Adaptation) to overcome challenges where some modalities appear more dominant than others during multimodal learning. MLA reframes the conventional joint multimodal learning process by transforming it into an alternating unimodal learning process. It captures cross-modal interactions through a shared head, which undergoes continuous optimization across different modalities. Experiments are conducted on five diverse datasets, encompassing scenarios with complete modalities and scenarios with missing modalities.
  arXiv  Detail & Related papers  (2023-11-17T18:57:40Z)
• 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)
• 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)
• CLIP-Driven Fine-grained Text-Image Person Re-identification [50.94827165464813]
  TIReID aims to retrieve the image corresponding to the given text query from a pool of candidate images. We propose a CLIP-driven Fine-grained information excavation framework (CFine) to fully utilize the powerful knowledge of CLIP for TIReID.
  arXiv  Detail & Related papers  (2022-10-19T03:43:12Z)

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.