paper-with-me

홈 › Papers

Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages

2023-06-29 · Yasmine Karoui, Rémi Lebret, Negar Foroutan, Karl Aberer

Vision-Language Pre-training (VLP) has advanced the performance of many vision-language tasks, such as image-text retrieval, visual entailment, and visual reasoning. The pre-training mostly utilizes lexical databases and image queries in English. Previous work has demonstrated that the pre-training in English does not transfer well to other languages in a zero-shot setting. However, multilingual pre-trained language models (MPLM) have excelled at a variety of single-modal language tasks. In this paper, we propose a simple yet efficient approach to adapt VLP to unseen languages using MPLM. We utilize a cross-lingual contextualized token embeddings alignment approach to train text encoders for non-English languages. Our approach does not require image input and primarily uses machine translation, eliminating the need for target language data. Our evaluation across three distinct tasks (image-text retrieval, visual entailment, and natural language visual reasoning) demonstrates that this approach outperforms the state-of-the-art multilingual vision-language models without requiring large parallel corpora. Our code is available at https://github.com/Yasminekaroui/CliCoTea.

📄 PDF Abstract BibTeX arXiv:2306.16774

Code (1)

yasminekaroui/clicotea 공식 구현 pytorch

Tasks

Image-text RetrievalMachine TranslationRetrievalText RetrievalVisual EntailmentVisual Reasoning

Similar Papers 제목 키워드 기반

GemNav: Discrete-Token Visual Robot Navigation using a Multimodal Large Language Model

2026-07-08 · Peter Bohm, Saimunur Rahman, Abdelwahed Khamis, Sagun Man Singh Shrestha 외 arxiv

Visual navigation policies built on large pretrained models have so far followed a common recipe: a dedicated visual encoder, a bespoke action head, and training on thousands of hours of cross-embodiment datasets. We ask…

Visual NavigationRobot Navigation

Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigation

2019-06-02 · ACL 2019 7 · Ronghang Hu, Daniel Fried, Anna Rohrbach, Dan Klein 외

Vision-and-Language Navigation (VLN) requires grounding instructions, such as "turn right and stop at the door", to routes in a visual environment. The actual grounding can connect language to the environment through mul…

Vision and Language Navigation

Histopath-C: Towards Realistic Domain Shifts for Histopathology Vision-Language Adaptation

2026-01-18 · Mehrdad Noori, Gustavo Adolfo Vargas Hakim, David Osowiechi, Fereshteh Shakeri 외 arxiv

Medical Vision-language models (VLMs) have shown remarkable performances in various medical imaging domains such as histo\-pathology by leveraging pre-trained, contrastive models that exploit visual and textual informati…

Test-time Adaptation

EGA: Adapting Frozen Encoders for Vector Search with Bounded Out-of-Distribution Degradation

2026-05-07 · Dongfang Zhao arxiv

Vector search systems built on frozen vision encoders face queries from unseen classes at deployment, yet existing adapter training collapses under this shift: high-capacity adapters with global contrastive losses silent…

Dual Adaptive Pyramid Network for Cross-Stain Histopathology Image Segmentation

2019-09-25 · Xianxu Hou, Jingxin Liu, Bolei Xu, Bozhi Liu 외

Supervised semantic segmentation normally assumes the test data being in a similar data domain as the training data. However, in practice, the domain mismatch between the training and unseen data could lead to a signific…

Domain AdaptationImage SegmentationSegmentationSemantic Segmentation