Abstract
Methods of Explainable AI (XAI) are popular for understanding the features and decisions of neural networks. Transformers used for single modalities such as videos, texts, or signals as well as multi-modal data can be considered as a state-of-the-art model for various tasks such as classification, detection, segmentation, etc. as they generalize better than conventional CNNs. The use of feature selection methods using interpretability techniques can be exciting to train the transformer models. This work proposes the use of an interpretability method based on attention gradients to highlight important attention weights along the training iterations. This guides the transformer parameters to evolve in a more optimal direction. This work considers a multimodal transformer on multimodal data: video and sensors. First studied on the video part of multimodal data, this strategy is applied to the sensor data in the proposed multimodal transformer architecture before fusion. We show that the late fusion via a combined loss from both modalities outperforms single-modality results. The target application of this approach is Multimedia in Health for the detection of risk situations for frail adults in the @home environment from the wearable video and sensor data (BIRDS dataset). We also benchmark our approach on the publicly available single-video Kinetics-400 dataset to assess the performance, which is indeed better than the state-of-the-art.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
BIRDS will be publicly available upon GDPR clearance.
References
Ayyar, M.P., Benois-Pineau, J., Zemmari, A.: Review of white box methods for explanations of convolutional neural networks in image classification tasks. J. Electron. Imaging 30(5), 050901 (2021)
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.R., Samek, W.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10(7), e0130140 (2015)
Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML (2021)
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213–229. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_13
Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on CVPR 2017
Chefer, H., Gur, S., Wolf, L.: Transformer interpretability beyond attention visualization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 782–791, June 2021
Chefer, H., Schwartz, I., Wolf, L.: Optimizing relevance maps of vision transformers improves robustness. In: NeuRIPS 2022
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)
Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR 2021
Feichtenhofer, C.: X3d: expanding architectures for efficient video recognition. In: 2020 IEEE/CVF Conference on CVPR (2020)
Guo, X., Guo, X., Lu, Y.: SSAN: separable self-attention network for video representation learning. In: Proceedings of the IEEE/CVF CVPR 2021
Li, Q., Qiu, Z., Yao, T., Mei, T., Rui, Y., Luo, J.: Action recognition by learning deep multi-granular spatio-temporal video representation. In: Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval. ACM (2016)
Liang, H., et al.: Training interpretable convolutional neural networks by differentiating class-specific filters. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 622–638. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58536-5_37
Liu, K., Li, Y., Xu, N., Natarajan, P.: Learn to combine modalities in multimodal deep learning. ArXiv abs/1805.11730 (2018)
Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 10012–10022, October 2021
Liu, Z., et al.: Video swin transformer. arXiv preprint arXiv:2106.13230 (2021)
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Guyon, I., et al. (eds.) Advances in NeuRIPS 2017
Mallick, R., Benois-Pineau, J., Zemmari, A.: I saw: a self-attention weighted method for explanation of visual transformers. In: IEEE ICIP 2022
Mallick, R., et al.: Pooling transformer for detection of risk events in in-the-wild video ego data. In: 26th ICPR 2022
Mallick, R., Yebda, T., Benois-Pineau, J., Zemmari, A., Pech, M., Amieva, H.: Detection of risky situations for frail adults with hybrid neural networks on multimodal health data. IEEE Multim. 29(1), 7–17 (2022)
Meditskos, G., Plans, P., Stavropoulos, T.G., Benois-Pineau, J., Buso, V., Kompatsiaris, I.: Multi-modal activity recognition from egocentric vision, semantic enrichment and lifelogging applications for the care of dementia. J. Vis. Commun. Image Represent. 51, 169–190 (2018)
Montavon, G., Lapuschkin, S., Binder, A., Samek, W., Müller, K.R.: Explaining nonlinear classification decisions with deep Taylor decomposition. Pattern Recogn. 65, 211–222 (2017)
Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: Proceedings of the 28th ICML 2011
Owens, A., Efros, A.A.: Audio-visual scene analysis with self-supervised multisensory features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 639–658. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01231-1_39
Radford, A., et al.: Learning transferable visual models from natural language supervision (2021)
Ribeiro, M.T., Singh, S., Guestrin, C.: “Why should I trust you?: Explaining the predictions of any classifier. In: KDD, pp. 1135–1144. ACM (2016)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE/CVF ICCV (2017)
Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS (2014)
Springenberg, J., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: the all convolutional net, December 2014
Srinivas, A., Lin, T.Y., Parmar, N., Shlens, J., Abbeel, P., Vaswani, A.: Bottleneck transformers for visual recognition. In: CVPR (2021)
Srinivas, S., Fleuret, F.: Full-gradient representation for neural network visualization. In: Advances in Neural Information Processing Systems (2019)
Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 4489–4497, December 2015
Tran, D., Wang, H., Torresani, L., Feiszli, M.: Video classification with channel-separated convolutional networks. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2019
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Wang, S., Li, B.Z., Khabsa, M., Fang, H., Ma, H.: Linformer: self-attention with linear complexity (2020). https://arxiv.org/abs/2006.04768
Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018
Yebda, T., Benois-Pineau, J., Pech, M., Amieva, H., Middleton, L., Bergelt, M.: Multimodal sensor data analysis for detection of risk situations of fragile people in @home environments. In: Lokoč, J., et al. (eds.) MMM 2021. LNCS, vol. 12573, pp. 342–353. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-67835-7_29
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53
Zhang, H., Torres, F., Sicre, R., Avrithis, Y., Ayache, S.: Opti-CAM: optimizing saliency maps for interpretability. CoRR abs/2301.07002 (2023)
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2921–2929 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Mallick, R., Benois-Pineau, J., Zemmari, A. (2024). IFI: Interpreting for Improving: A Multimodal Transformer with an Interpretability Technique for Recognition of Risk Events. In: Rudinac, S., et al. MultiMedia Modeling. MMM 2024. Lecture Notes in Computer Science, vol 14557. Springer, Cham. https://doi.org/10.1007/978-3-031-53302-0_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-53302-0_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-53301-3
Online ISBN: 978-3-031-53302-0
eBook Packages: Computer ScienceComputer Science (R0)