COMPASS: Complete Multimodal Fusion via Proxy Tokens and Shared Spaces for Ubiquitous Sensing

• URL: http://arxiv.org/abs/2604.02056v1
• Date: Thu, 02 Apr 2026 13:55:24 GMT
• Title: COMPASS: Complete Multimodal Fusion via Proxy Tokens and Shared Spaces for Ubiquitous Sensing
• Abstract summary: We propose a missing-modality fusion framework built on the principle of fusion completeness.<n>For each missing modality, we synthesize a target-specific proxy token from the observed modalities.<n>Experiments on XRF55, MM-Fi, and OctoNet under diverse single- and multiple-missing settings show that our framework outperforms prior methods.
• Score: 7.598111859541752
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Missing modalities remain a major challenge for multimodal sensing, because most existing methods adapt the fusion process to the observed subset by dropping absent branches, using subset-specific fusion, or reconstructing missing features. As a result, the fusion head often receives an input structure different from the one seen during training, leading to incomplete fusion and degraded cross-modal interaction. We propose COMPASS, a missing-modality fusion framework built on the principle of fusion completeness: the fusion head always receives a fixed N-slot multimodal input, with one token per modality slot. For each missing modality, COMPASS synthesizes a target-specific proxy token from the observed modalities using pairwise source-to-target generators in a shared latent space, and aggregates them into a single replacement token. To make these proxies both representation-compatible and task-informative, we combine proxy alignment, shared-space regularization, and per-proxy discriminative supervision. Experiments on XRF55, MM-Fi, and OctoNet under diverse single- and multiple-missing settings show that COMPASS outperforms prior methods on the large majority of scenarios. Our results suggest that preserving a modality-complete fusion interface is a simple and effective design principle for robust multimodal sensing.

Related papers

• MODAL: Multi-Modal Object Re-ID via Model-Driven Sparse Decoupling and Text-Image Differential Filtering [51.99452481869329]
  MODAL is a novel multi-modal object re-identification framework grounded in coupled sparse coding theory and differential suppression principles.<n>A core component of MODAL is a Multi-modal Feature Sparse Decoupling module, developed in a model-driven deep unrolling manner.<n>Benefiting from the principled feature disentanglement, MODAL naturally mitigates performance degradation in incomplete-modality scenarios.<n>Experiments on four datasets demonstrate that MODAL achieves state-of-the-art performance with superior transparency.
  arXiv  Detail & Related papers  (2026-08-15T07:41:10Z)
• Parameter-Efficient Modality-Balanced Symmetric Fusion for Multimodal Remote Sensing Semantic Segmentation [8.840077295284393]
  MoBaNet is a parameter-efficient and modality-balanced symmetric fusion framework.<n>Built upon a largely frozen VFM backbone, MoBaNet adopts a symmetric dual-stream architecture to preserve generalizable representations.<n>Experiments on the ISPRS Vaihingen and Potsdam benchmarks demonstrate that MoBaNet achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-03-18T13:23:58Z)
• SiMO: Single-Modality-Operable Multimodal Collaborative Perception [21.057627256755385]
  This paper introduces Single-Modality-Operable Multimodal Collaborative Perception (SiMO)<n>By adopting the proposed Length-Adaptive Multi-Modal Fusion (LAMMA), SiMO can adaptively handle remaining modal features during modal failures.<n>Experiments demonstrate that SiMO effectively aligns multimodal features while simultaneously preserving modality-specific features.
  arXiv  Detail & Related papers  (2026-03-09T11:09:53Z)
• Complementarity-Supervised Spectral-Band Routing for Multimodal Emotion Recognition [60.20529806857076]
  Multimodal emotion recognition fuses cues such as text, video, and audio to understand individual emotional states.<n>Prior methods face two main limitations: mechanically relying on independent unimodal performance, and coarse-grained fusion conflicting with the fine-grained representations required by emotion tasks.<n>We propose the Complementarity-Supervised Multi-Band Expert Network, named Atsuko, to model fine-grained complementary features via multi-scale band decomposition and expert collaboration.
  arXiv  Detail & Related papers  (2026-03-07T03:58:48Z)
• Feature-level Interaction Explanations in Multimodal Transformers [1.7101146971136896]
  Multimodal Transformers produce predictions without clarifying how different modalities jointly support a decision.<n>We present Feature-level I2MoE, a structured Mixture-of-Experts layer that operates directly on token/patch sequences from frozen pretrained encoders.<n>We develop an expert-wise explanation pipeline that combines attribution with top-K% masking to assess faithfulness.
  arXiv  Detail & Related papers  (2026-03-04T18:24:31Z)
• UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation [104.59740403500132]
  Multi-modal image segmentation faces real-world deployment challenges from incomplete/corrupted modalities degrading performance.<n>We propose a unified modality-relax segmentation network (UniMRSeg) through hierarchical self-supervised compensation (HSSC)<n>Our approach hierarchically bridges representation gaps between complete and incomplete modalities across input, feature and output levels.
  arXiv  Detail & Related papers  (2025-09-19T17:29:25Z)
• BiXFormer: A Robust Framework for Maximizing Modality Effectiveness in Multi-Modal Semantic Segmentation [55.486872677160015]
  We reformulate multi-modal semantic segmentation as a mask-level classification task.<n>We propose BiXFormer, which integrates Unified Modality Matching (UMM) and Cross Modality Alignment (CMA)<n> Experiments on both synthetic and real-world multi-modal benchmarks demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2025-06-04T08:04:58Z)
• Part-Whole Relational Fusion Towards Multi-Modal Scene Understanding [51.96911650437978]
  Multi-modal fusion has played a vital role in multi-modal scene understanding. Most existing methods focus on cross-modal fusion involving two modalities, often overlooking more complex multi-modal fusion. We propose a relational Part-Whole Fusion (PWRF) framework for multi-modal scene understanding.
  arXiv  Detail & Related papers  (2024-10-19T02:27:30Z)
• Object Segmentation by Mining Cross-Modal Semantics [68.88086621181628]
  We propose a novel approach by mining the Cross-Modal Semantics to guide the fusion and decoding of multimodal features. Specifically, we propose a novel network, termed XMSNet, consisting of (1) all-round attentive fusion (AF), (2) coarse-to-fine decoder (CFD), and (3) cross-layer self-supervision.
  arXiv  Detail & Related papers  (2023-05-17T14:30:11Z)
• ScaleVLAD: Improving Multimodal Sentiment Analysis via Multi-Scale Fusion of Locally Descriptors [15.042741192427334]
  This paper proposes a fusion model named ScaleVLAD to gather multi-Scale representation from text, video, and audio. Experiments on three popular sentiment analysis benchmarks, IEMOCAP, MOSI, and MOSEI, demonstrate significant gains over baselines.
  arXiv  Detail & Related papers  (2021-12-02T16:09:33Z)
• Learning Deep Multimodal Feature Representation with Asymmetric Multi-layer Fusion [63.72912507445662]
  We propose a compact and effective framework to fuse multimodal features at multiple layers in a single network. We verify that multimodal features can be learnt within a shared single network by merely maintaining modality-specific batch normalization layers in the encoder. Secondly, we propose a bidirectional multi-layer fusion scheme, where multimodal features can be exploited progressively.
  arXiv  Detail & Related papers  (2021-08-11T03:42:13Z)

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.