2023-09-02 更新
CLIPTrans: Transferring Visual Knowledge with Pre-trained Models for Multimodal Machine Translation
Authors:Devaansh Gupta, Siddhant Kharbanda, Jiawei Zhou, Wanhua Li, Hanspeter Pfister, Donglai Wei
There has been a growing interest in developing multimodal machine translation (MMT) systems that enhance neural machine translation (NMT) with visual knowledge. This problem setup involves using images as auxiliary information during training, and more recently, eliminating their use during inference. Towards this end, previous works face a challenge in training powerful MMT models from scratch due to the scarcity of annotated multilingual vision-language data, especially for low-resource languages. Simultaneously, there has been an influx of multilingual pre-trained models for NMT and multimodal pre-trained models for vision-language tasks, primarily in English, which have shown exceptional generalisation ability. However, these are not directly applicable to MMT since they do not provide aligned multimodal multilingual features for generative tasks. To alleviate this issue, instead of designing complex modules for MMT, we propose CLIPTrans, which simply adapts the independently pre-trained multimodal M-CLIP and the multilingual mBART. In order to align their embedding spaces, mBART is conditioned on the M-CLIP features by a prefix sequence generated through a lightweight mapping network. We train this in a two-stage pipeline which warms up the model with image captioning before the actual translation task. Through experiments, we demonstrate the merits of this framework and consequently push forward the state-of-the-art across standard benchmarks by an average of +2.67 BLEU. The code can be found at www.github.com/devaansh100/CLIPTrans.
PDF 15 pages, 9 figures, to be published In Proceedings of International Conference of Computer Vision(ICCV), 2023
点此查看论文截图
Document AI: A Comparative Study of Transformer-Based, Graph-Based Models, and Convolutional Neural Networks For Document Layout Analysis
Authors:Sotirios Kastanas, Shaomu Tan, Yi He
Document AI aims to automatically analyze documents by leveraging natural language processing and computer vision techniques. One of the major tasks of Document AI is document layout analysis, which structures document pages by interpreting the content and spatial relationships of layout, image, and text. This task can be image-centric, wherein the aim is to identify and label various regions such as authors and paragraphs, or text-centric, where the focus is on classifying individual words in a document. Although there are increasingly sophisticated methods for improving layout analysis, doubts remain about the extent to which their findings can be generalized to a broader context. Specifically, prior work developed systems based on very different architectures, such as transformer-based, graph-based, and CNNs. However, no work has mentioned the effectiveness of these models in a comparative analysis. Moreover, while language-independent Document AI models capable of knowledge transfer have been developed, it remains to be investigated to what degree they can effectively transfer knowledge. In this study, we aim to fill these gaps by conducting a comparative evaluation of state-of-the-art models in document layout analysis and investigating the potential of cross-lingual layout analysis by utilizing machine translation techniques.
PDF
点此查看论文截图
Impact of Visual Context on Noisy Multimodal NMT: An Empirical Study for English to Indian Languages
Authors:Baban Gain, Dibyanayan Bandyopadhyay, Samrat Mukherjee, Chandranath Adak, Asif Ekbal
The study investigates the effectiveness of utilizing multimodal information in Neural Machine Translation (NMT). While prior research focused on using multimodal data in low-resource scenarios, this study examines how image features impact translation when added to a large-scale, pre-trained unimodal NMT system. Surprisingly, the study finds that images might be redundant in this context. Additionally, the research introduces synthetic noise to assess whether images help the model deal with textual noise. Multimodal models slightly outperform text-only models in noisy settings, even with random images. The study’s experiments translate from English to Hindi, Bengali, and Malayalam, outperforming state-of-the-art benchmarks significantly. Interestingly, the effect of visual context varies with source text noise: no visual context works best for non-noisy translations, cropped image features are optimal for low noise, and full image features work better in high-noise scenarios. This sheds light on the role of visual context, especially in noisy settings, opening up a new research direction for Noisy Neural Machine Translation in multimodal setups. The research emphasizes the importance of combining visual and textual information for improved translation in various environments.
PDF
点此查看论文截图
MedShapeNet — A Large-Scale Dataset of 3D Medical Shapes for Computer Vision
Authors:Jianning Li, Antonio Pepe, Christina Gsaxner, Gijs Luijten, Yuan Jin, Narmada Ambigapathy, Enrico Nasca, Naida Solak, Gian Marco Melito, Afaque R. Memon, Xiaojun Chen, Jan Stefan Kirschke, Ezequiel de la Rosa, Patrich Ferndinand Christ, Hongwei Bran Li, David G. Ellis, Michele R. Aizenberg, Sergios Gatidis, Thomas Kuestner, Nadya Shusharina, Nicholas Heller, Vincent Andrearczyk, Adrien Depeursinge, Mathieu Hatt, Anjany Sekuboyina, Maximilian Loeffler, Hans Liebl, Reuben Dorent, Tom Vercauteren, Jonathan Shapey, Aaron Kujawa, Stefan Cornelissen, Patrick Langenhuizen, Achraf Ben-Hamadou, Ahmed Rekik, Sergi Pujades, Edmond Boyer, Federico Bolelli, Costantino Grana, Luca Lumetti, Hamidreza Salehi, Jun Ma, Yao Zhang, Ramtin Gharleghi, Susann Beier, Arcot Sowmya, Eduardo A. Garza-Villarreal, Thania Balducci, Diego Angeles-Valdez, Roberto Souza, Leticia Rittner, Richard Frayne, Yuanfeng Ji, Soumick Chatterjee, Andreas Nuernberger, Joao Pedrosa, Carlos Ferreira, Guilherme Aresta, Antonio Cunha, Aurelio Campilho, Yannick Suter, Jose Garcia, Alain Lalande, Emmanuel Audenaert, Claudia Krebs, Timo Van Leeuwen, Evie Vereecke, Rainer Roehrig, Frank Hoelzle, Vahid Badeli, Kathrin Krieger, Matthias Gunzer, Jianxu Chen, Amin Dada, Miriam Balzer, Jana Fragemann, Frederic Jonske, Moritz Rempe, Stanislav Malorodov, Fin H. Bahnsen, Constantin Seibold, Alexander Jaus, Ana Sofia Santos, Mariana Lindo, Andre Ferreira, Victor Alves, Michael Kamp, Amr Abourayya, Felix Nensa, Fabian Hoerst, Alexander Brehmer, Lukas Heine, Lars E. Podleska, Matthias A. Fink, Julius Keyl, Konstantinos Tserpes, Moon-Sung Kim, Shireen Elhabian, Hans Lamecker, Dzenan Zukic, Beatriz Paniagua, Christian Wachinger, Martin Urschler, Luc Duong, Jakob Wasserthal, Peter F. Hoyer, Oliver Basu, Thomas Maal, Max J. H. Witjes, Ping Luo, Bjoern Menze, Mauricio Reyes, Christos Davatzikos, Behrus Puladi, Jens Kleesiek, Jan Egger
We present MedShapeNet, a large collection of anatomical shapes (e.g., bones, organs, vessels) and 3D surgical instrument models. Prior to the deep learning era, the broad application of statistical shape models (SSMs) in medical image analysis is evidence that shapes have been commonly used to describe medical data. Nowadays, however, state-of-the-art (SOTA) deep learning algorithms in medical imaging are predominantly voxel-based. In computer vision, on the contrary, shapes (including, voxel occupancy grids, meshes, point clouds and implicit surface models) are preferred data representations in 3D, as seen from the numerous shape-related publications in premier vision conferences, such as the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), as well as the increasing popularity of ShapeNet (about 51,300 models) and Princeton ModelNet (127,915 models) in computer vision research. MedShapeNet is created as an alternative to these commonly used shape benchmarks to facilitate the translation of data-driven vision algorithms to medical applications, and it extends the opportunities to adapt SOTA vision algorithms to solve critical medical problems. Besides, the majority of the medical shapes in MedShapeNet are modeled directly on the imaging data of real patients, and therefore it complements well existing shape benchmarks comprising of computer-aided design (CAD) models. MedShapeNet currently includes more than 100,000 medical shapes, and provides annotations in the form of paired data. It is therefore also a freely available repository of 3D models for extended reality (virtual reality - VR, augmented reality - AR, mixed reality - MR) and medical 3D printing. This white paper describes in detail the motivations behind MedShapeNet, the shape acquisition procedures, the use cases, as well as the usage of the online shape search portal: https://medshapenet.ikim.nrw/
PDF 20 pages
点此查看论文截图