GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer

• URL: http://arxiv.org/abs/2406.01210v2
• Date: Tue, 4 Jun 2024 03:14:19 GMT
• Title: GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer
• Authors: Ding Jia, Jianyuan Guo, Kai Han, Han Wu, Chao Zhang, Chang Xu, Xinghao Chen,
• Abstract summary: Cross-modal transformers have demonstrated superiority in various vision tasks by effectively integrating different modalities. We propose GeminiFusion, a pixel-wise fusion approach that capitalizes on aligned cross-modal representations. We employ a layer-adaptive noise to adaptively control their interplay on a per-layer basis, thereby achieving a harmonized fusion process.
• Score: 44.44603063754173
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cross-modal transformers have demonstrated superiority in various vision tasks by effectively integrating different modalities. This paper first critiques prior token exchange methods which replace less informative tokens with inter-modal features, and demonstrate exchange based methods underperform cross-attention mechanisms, while the computational demand of the latter inevitably restricts its use with longer sequences. To surmount the computational challenges, we propose GeminiFusion, a pixel-wise fusion approach that capitalizes on aligned cross-modal representations. GeminiFusion elegantly combines intra-modal and inter-modal attentions, dynamically integrating complementary information across modalities. We employ a layer-adaptive noise to adaptively control their interplay on a per-layer basis, thereby achieving a harmonized fusion process. Notably, GeminiFusion maintains linear complexity with respect to the number of input tokens, ensuring this multimodal framework operates with efficiency comparable to unimodal networks. Comprehensive evaluations across multimodal image-to-image translation, 3D object detection and arbitrary-modal semantic segmentation tasks, including RGB, depth, LiDAR, event data, etc. demonstrate the superior performance of our GeminiFusion against leading-edge techniques. The PyTorch code is available at https://github.com/JiaDingCN/GeminiFusion

Related papers

• Hyper-Transformer for Amodal Completion [82.4118011026855]
  Amodal object completion is a complex task that involves predicting the invisible parts of an object based on visible segments and background information. We introduce a novel framework named the Hyper-Transformer Amodal Network (H-TAN) This framework utilizes a hyper transformer equipped with a dynamic convolution head to directly learn shape priors and accurately predict amodal masks.
  arXiv  Detail & Related papers  (2024-05-30T11:11:54Z)
• Cross-BERT for Point Cloud Pretraining [61.762046503448936]
  We propose a new cross-modal BERT-style self-supervised learning paradigm, called Cross-BERT. To facilitate pretraining for irregular and sparse point clouds, we design two self-supervised tasks to boost cross-modal interaction. Our work highlights the effectiveness of leveraging cross-modal 2D knowledge to strengthen 3D point cloud representation and the transferable capability of BERT across modalities.
  arXiv  Detail & Related papers  (2023-12-08T08:18:12Z)
• Exchanging-based Multimodal Fusion with Transformer [19.398692598523454]
  We study the problem of multimodal fusion in this paper. Recent exchanging-based methods have been proposed for vision-vision fusion, which aim to exchange embeddings learned from one modality to the other. We propose a novel exchanging-based multimodal fusion model MuSE for text-vision fusion based on Transformer.
  arXiv  Detail & Related papers  (2023-09-05T12:48:25Z)
• 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)
• Multimodal Token Fusion for Vision Transformers [54.81107795090239]
  We propose a multimodal token fusion method (TokenFusion) for transformer-based vision tasks. To effectively fuse multiple modalities, TokenFusion dynamically detects uninformative tokens and substitutes these tokens with projected and aggregated inter-modal features. The design of TokenFusion allows the transformer to learn correlations among multimodal features, while the single-modal transformer architecture remains largely intact.
  arXiv  Detail & Related papers  (2022-04-19T07:47:50Z)
• LMR-CBT: Learning Modality-fused Representations with CB-Transformer for Multimodal Emotion Recognition from Unaligned Multimodal Sequences [5.570499497432848]
  We propose an efficient neural network to learn modality-fused representations with CB-Transformer (LMR-CBT) for multimodal emotion recognition. We conduct word-aligned and unaligned experiments on three challenging datasets.
  arXiv  Detail & Related papers  (2021-12-03T03:43:18Z)
• 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.