CLIPTrans: Transferring Visual Knowledge with Pre-trained Models for Multimodal Machine Translation
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.
Code (1)
Tasks
Image CaptioningMachine TranslationMultimodal Machine TranslationNMTTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Few-shot Action Recognition with Captioning Foundation Models
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 RecognitionMultimodal Few-Shot Learning with Frozen Language Models
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+2Learning Robust Anymodal Segmentor with Unimodal and Cross-modal Distillation
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
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+3Transferring Knowledge from Vision to Language: How to Achieve it and how to Measure it?
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