# DRDF: Determining the Importance of Different Multimodal Information with Dual-Router Dynamic Framework

arXiv: https://arxiv.org/abs/2107.09909 · HTML: https://mlsanity.com/paper/2107.09909/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 28 references that are in the map.
- First posted on arXiv 21 Jul 2021.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training](https://mlsanity.com/paper/1908.06066/) (2019)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)
- [CondConv: Conditionally Parameterized Convolutions for Efficient Inference](https://mlsanity.com/paper/1904.04971/) (2019)
- [Gated Multimodal Units for Information Fusion](https://mlsanity.com/paper/1702.01992/) (2017)
- [SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning](https://mlsanity.com/paper/1611.05594/) (2016)
- [Supervised Multimodal Bitransformers for Classifying Images and Text](https://mlsanity.com/paper/1909.02950/) (2019)
- [Attention-Based Multimodal Fusion for Video Description](https://mlsanity.com/paper/1701.03126/) (2017)
- [Squeeze-and-Attention Networks for Semantic Segmentation](https://mlsanity.com/paper/1909.03402/) (2019)
- [NBDT: Neural-Backed Decision Trees](https://mlsanity.com/paper/2004.00221/) (2020)
- [Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation](https://mlsanity.com/paper/1910.02940/) (2019)
- [Long-Tailed Recognition Using Class-Balanced Experts](https://mlsanity.com/paper/2004.03706/) (2020)

## Abstract (arXiv)

In multimodal tasks, we find that the importance of text and image modal information is different for different input cases, and for this motivation, we propose a high-performance and highly general Dual-Router Dynamic Framework (DRDF), consisting of Dual-Router, MWF-Layer, experts and expert fusion unit. The text router and image router in Dual-Router accept text modal information and image modal information, and use MWF-Layer to determine the importance of modal information. Based on the result of the determination, MWF-Layer generates fused weights for the fusion of experts. Experts are model backbones that match the current task. DRDF has high performance and high generality, and we have tested 12 backbones such as Visual BERT on multimodal dataset Hateful memes, unimodal dataset CIFAR10, CIFAR100, and TinyImagenet. Our DRDF outperforms all the baselines. We also verified the components of DRDF in detail by ablations, compared and discussed the reasons and ideas of DRDF design.