paper-with-me

홈 › Papers

How to Adapt Pre-trained Vision-and-Language Models to a Text-only Input?

2022-09-19 · COLING 2022 10 · Lovisa Hagström, Richard Johansson

Current language models have been criticised for learning language from text alone without connection between words and their meaning. Consequently, multimodal training has been proposed as a way for creating models with better language understanding by providing the lacking connection. We focus on pre-trained multimodal vision-and-language (VL) models for which there already are some results on their language understanding capabilities. An unresolved issue with evaluating the linguistic skills of these models, however, is that there is no established method for adapting them to text-only input without out-of-distribution uncertainty. To find the best approach, we investigate and compare seven possible methods for adapting three different pre-trained VL models to text-only input. Our evaluations on both GLUE and Visual Property Norms (VPN) show that care should be put into adapting VL models to zero-shot text-only tasks, while the models are less sensitive to how we adapt them to non-zero-shot tasks. We also find that the adaptation methods perform differently for different models and that unimodal model counterparts perform on par with the VL models regardless of adaptation, indicating that current VL models do not necessarily gain better language understanding from their multimodal training.

📄 PDF Abstract BibTeX arXiv:2209.08982

Code (1)

lovhag/adapt-pre-trained-vl-models-to-text 공식 구현 pytorch

Similar Papers 제목 키워드 기반

VLSM-Adapter: Finetuning Vision-Language Segmentation Efficiently with Lightweight Blocks

2024-05-10 · Manish Dhakal, Rabin Adhikari, Safal Thapaliya, Bishesh Khanal

Foundation Vision-Language Models (VLMs) trained using large-scale open-domain images and text pairs have recently been adapted to develop Vision-Language Segmentation Models (VLSMs) that allow providing text prompts dur…

Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation+1

In-context Prompt Learning for Test-time Vision Recognition with Frozen Vision-language Model

2024-03-10 · Junhui Yin, Xinyu Zhang, Lin Wu, Xiaojie Wang

Current pre-trained vision-language models, such as CLIP, have demonstrated remarkable zero-shot generalization capabilities across various downstream tasks. However, their performance significantly degrades when test in…

In-Context LearningLanguage ModelingLanguage ModellingPrompt Learning+1

Optimizing Vision-Language Interactions Through Decoder-Only Models

2024-12-14 · Kaito Tanaka, Benjamin Tan, Brian Wong

Vision-Language Models (VLMs) have emerged as key enablers for multimodal tasks, but their reliance on separate visual encoders introduces challenges in efficiency, scalability, and modality alignment. To address these l…

DecoderImage CaptioningLanguage ModelingLanguage Modelling+2

Efficient Medical Vision-Language Alignment Through Adapting Masked Vision Models

2025-06-10 · Chenyu Lian, Hong-Yu Zhou, Dongyun Liang, Jing Qin 외

Medical vision-language alignment through cross-modal contrastive learning shows promising performance in image-text matching tasks, such as retrieval and zero-shot classification. However, conventional cross-modal contr…

Contrastive LearningImage-text matchingImage to textImage-to-Text Retrieval+5

Towards Versatile and Efficient Visual Knowledge Integration into Pre-trained Language Models with Cross-Modal Adapters

2023-05-12 · Xinyun Zhang, Haochen Tan, Han Wu, Bei Yu

Humans learn language via multi-modal knowledge. However, due to the text-only pre-training scheme, most existing pre-trained language models (PLMs) are hindered from the multi-modal information. To inject visual knowled…

Natural Language Understanding