paper-with-me

Papers

CLIPTrans: Transferring Visual Knowledge with Pre-trained Models for Multimodal Machine Translation

2023-08-29 · ICCV 2023 1 · 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 Abstract BibTeX arXiv:2308.15226

Code (1)

devaansh100/cliptrans 공식 구현 pytorch

Tasks

Image CaptioningMachine TranslationMultimodal Machine TranslationNMTTranslation

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
mBART 설명 없음

Similar Papers 제목 키워드 기반

Few-shot Action Recognition with Captioning Foundation Models

2023-10-16 · Xiang Wang, Shiwei Zhang, Hangjie Yuan, Yingya Zhang 외

Transferring vision-language knowledge from pretrained multimodal foundation models to various downstream tasks is a promising direction. However, most current few-shot action recognition methods are still limited to a s…

Action RecognitionFew-Shot action recognitionFew Shot Action Recognition

Multimodal Few-Shot Learning with Frozen Language Models

2021-06-25 · NeurIPS 2021 12 · Maria Tsimpoukelli, Jacob Menick, Serkan Cabi, S. M. Ali Eslami 외

When trained at sufficient scale, auto-regressive language models exhibit the notable ability to learn a new language task after being prompted with just a few examples. Here, we present a simple, yet effective, approach…

Few-Shot LearningLanguage ModelingLanguage ModellingQuestion Answering+2

Learning Robust Anymodal Segmentor with Unimodal and Cross-modal Distillation

2024-11-26 · Xu Zheng, Haiwei Xue, Jialei Chen, Yibo Yan 외

Simultaneously using multimodal inputs from multiple sensors to train segmentors is intuitively advantageous but practically challenging. A key challenge is unimodal bias, where multimodal segmentors over rely on certain…

Embodied Multimodal Multitask Learning

2019-02-04 · Devendra Singh Chaplot, Lisa Lee, Ruslan Salakhutdinov, Devi Parikh 외

Recent efforts on training visual navigation agents conditioned on language using deep reinforcement learning have been successful in learning policies for different multimodal tasks, such as semantic goal navigation and…

Deep Reinforcement LearningDisentanglementEmbodied Question AnsweringQuestion Answering+3

Transferring Knowledge from Vision to Language: How to Achieve it and how to Measure it?

2021-09-23 · EMNLP (BlackboxNLP) 2021 11 · Tobias Norlund, Lovisa Hagström, Richard Johansson

Large language models are known to suffer from the hallucination problem in that they are prone to output statements that are false or inconsistent, indicating a lack of knowledge. A proposed solution to this is to provi…

HallucinationTransfer Learning