ABSTRACT
In multimodal tasks, the importance of text and image modal information often varies for different input cases. To model the difference of importance of different modal information, 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 take text modal information and image modal information respectively, and MWF-Layer is responsible to determine the importance of modal information. Based on the result of the determination, MWF-Layer generates fused weights for the subsequent experts fusion. Experts can adopt a variety of backbones that match the current multimodal or unimodal task. DRDF features high generality and modularity, and we test 12 backbones such as Visual BERT and their corresponding DRDF instances on the multimodal dataset Hateful memes, and unimodal datasets CIFAR10, CIFAR100, and TinyImagenet. Our DRDF instance outperforms those backbones. We also validate the effectiveness of components of DRDF by ablation studies, and discuss the reasons and ideas of DRDF design.
- Long Chen, Hanwang Zhang, Jun Xiao, Liqiang Nie, Jian Shao, Wei Liu, and Tat-Seng Chua. 2017. Sca-cnn: Spatial and channel-wise attention in convolutional networks for image captioning. In Proceedings of the IEEE conference on computer vision and pattern recognition. 5659--5667.Google ScholarCross Ref
- Yinpeng Chen, Xiyang Dai, Mengchen Liu, Dongdong Chen, Lu Yuan, and Zicheng Liu. 2020. Dynamic convolution: Attention over convolution kernels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11030--11039.Google ScholarCross Ref
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT (1).Google Scholar
- Hang Gao, Xizhou Zhu, Stephen Lin, and Jifeng Dai. 2019. Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation. In International Conference on Learning Representations.Google Scholar
- Yizeng Han, Gao Huang, Shiji Song, Le Yang, Honghui Wang, and Yulin Wang. 2021. Dynamic neural networks: A survey. arXiv preprint arXiv:2102.04906 (2021).Google Scholar
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770--778.Google ScholarCross Ref
- Chiori Hori, Takaaki Hori, Teng-Yok Lee, Ziming Zhang, Bret Harsham, John R Hershey, Tim K Marks, and Kazuhiko Sumi. 2017. Attention-based multimodal fusion for video description. In Proceedings of the IEEE international conference on computer vision. 4193--4202.Google ScholarCross Ref
- Jie Hu, Li Shen, and Gang Sun. 2018. Squeeze-and-excitation networks. In Proceed- ings of the IEEE conference on computer vision and pattern recognition. 7132--7141.Google Scholar
- Douwe Kiela, Suvrat Bhooshan, Hamed Firooz, and Davide Testuggine. 2019. Supervised multimodal bitransformers for classifying images and text. arXiv preprint arXiv:1909.02950 (2019).Google Scholar
- Douwe Kiela, Hamed Firooz, Aravind Mohan, Vedanuj Goswami, Amanpreet Singh, Pratik Ringshia, and Davide Testuggine. 2020. The Hateful Memes Chal- lenge: Detecting Hate Speech in Multimodal Memes. Advances in Neural Information Processing Systems 33 (2020).Google Scholar
- Alex Krizhevsky, Geoffrey Hinton, et al. 2009. Learning multiple layers of features from tiny images. (2009).Google Scholar
- Ya Le and Xuan Yang. 2015. Tiny imagenet visual recognition challenge. CS 231N 7 (2015).Google Scholar
- Gen Li, Nan Duan, Yuejian Fang, Ming Gong, and Daxin Jiang. 2020. Unicoder- vl: A universal encoder for vision and language by cross-modal pre-training. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 11336--11344.Google ScholarCross Ref
- Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang. 2019. Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019).Google Scholar
- Xiang Li, Wenhai Wang, Xiaolin Hu, and Jian Yang. 2019. Selective kernel networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 510--519.Google ScholarCross Ref
- Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In Proceedings of the 33rd International Conference on Neural Information Processing Systems. 13--23. Google ScholarDigital Library
- John Edison Arevalo Ovalle, Thamar Solorio, Manuel Montes-y Gómez, and Fabio A González. 2017. Gated Multimodal Units for Information Fusion.. In ICLR (Workshop).Google Scholar
- Piyush Sharma, Nan Ding, Sebastian Goodman, and Radu Soricut. 2018. Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2556--2565.Google ScholarCross Ref
- Saurabh Sharma, Ning Yu, Mario Fritz, and Bernt Schiele. 2021. Long-tailed recognition using class-balanced experts. In Pattern Recognition: 42nd DAGM German Conference, DAGM GCPR 2020, Tübingen, Germany, September 28-October 1, 2020, Proceedings 42. Springer, 86--100.Google ScholarCross Ref
- K Simonyan and A Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. (2015).Google Scholar
- Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, and Jifeng Dai. 2019. VL-BERT: Pre-training of Generic Visual-Linguistic Representations. In International Conference on Learning Representations.Google Scholar
- Hao Tan and Mohit Bansal. 2019. LXMERT: Learning Cross-Modality Encoder Representations from Transformers. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 5100--5111.Google ScholarCross Ref
- Alvin Wan, Lisa Dunlap, Daniel Ho, Jihan Yin, Scott Lee, Henry Jin, Suzanne Petryk, Sarah Adel Bargal, and Joseph E Gonzalez. 2020. NBDT: Neural-Backed Decision Trees. arXiv preprint arXiv:2004.00221 (2020).Google Scholar
- Sanghyun Woo, Jongchan Park, Joon-Young Lee, and In So Kweon. 2018. Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV). 3--19.Google ScholarDigital Library
- Brandon Yang, Gabriel Bender, Quoc V Le, and Jiquan Ngiam. 2019. Condconv: Conditionally parameterized convolutions for efficient inference. In Advances in Neural Information Processing Systems. 1307--1318. Google ScholarDigital Library
- Sergey Zagoruyko and Nikos Komodakis. 2016. Wide Residual Networks. In British Machine Vision Conference 2016. British Machine Vision Association.Google Scholar
- Zilong Zhong, Zhong Qiu Lin, Rene Bidart, Xiaodan Hu, Ibrahim Ben Daya, Zhifeng Li, Wei-Shi Zheng, Jonathan Li, and Alexander Wong. 2020. Squeeze-and- Attention Networks for Semantic Segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 13065--13074.Google ScholarCross Ref
Index Terms
- DRDF: Determining the Importance of Different Multimodal Information with Dual-Router Dynamic Framework
Recommendations
Rethinking Fusion Baselines for Multi-modal Human Action Recognition
Advances in Multimedia Information Processing – PCM 2018AbstractIn this paper we study fusion baselines for multi-modal action recognition. Our work explores different strategies for multiple stream fusion. First, we consider the early fusion which fuses the different modal inputs by directly stacking them ...
Understanding Conversational and Expressive Style in a Multimodal Embodied Conversational Agent
CHI '21: Proceedings of the 2021 CHI Conference on Human Factors in Computing SystemsEmbodied conversational agents have changed the ways we can interact with machines. However, these systems often do not meet users’ expectations. A limitation is that the agents are monotonic in behavior and do not adapt to an interlocutor. We present ...
Towards Multimodal Human-Like Characteristics and Expressive Visual Prosody in Virtual Agents
ICMI '20: Proceedings of the 2020 International Conference on Multimodal InteractionOne of the key challenges in designing Embodied Conversational Agents (ECA) is to produce human-like gestural and visual prosody expressivity. Another major challenge is to maintain the interlocutor's attention by adapting the agent's behavior to the ...
Comments