paper-with-me

Papers

Weakly-Supervised Learning of Visual Relations in Multimodal Pretraining

2023-05-23 · Emanuele Bugliarello, Aida Nematzadeh, Lisa Anne Hendricks

Recent work in vision-and-language pretraining has investigated supervised signals from object detection data to learn better, fine-grained multimodal representations. In this work, we take a step further and explore how we can tap into supervision from small-scale visual relation data. In particular, we propose two pretraining approaches to contextualise visual entities in a multimodal setup. With verbalised scene graphs, we transform visual relation triplets into structured captions, and treat them as additional image descriptions. With masked relation prediction, we further encourage relating entities from image regions with visually masked contexts. When applied to strong baselines pretrained on large amounts of Web data, zero-shot evaluations on both coarse-grained and fine-grained tasks show the efficacy of our methods in learning multimodal representations from weakly-supervised relations data.

📄 PDF Abstract BibTeX arXiv:2305.14281

Code (1)

e-bug/weak-relation-vlm 공식 구현 pytorch

Tasks

object-detectionObject DetectionRelationRelation PredictionWeakly-supervised Learning

Similar Papers 제목 키워드 기반

Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations

2021-08-12 · Josh Beal, Hao-Yu Wu, Dong Huk Park, Andrew Zhai 외

Large-scale pretraining of visual representations has led to state-of-the-art performance on a range of benchmark computer vision tasks, yet the benefits of these techniques at extreme scale in complex production systems…

Image ClassificationMulti-Task LearningRepresentation LearningRetrieval

Exploring the Limits of Weakly Supervised Pretraining

2018-05-02 · ECCV 2018 9 · Dhruv Mahajan, Ross Girshick, Vignesh Ramanathan, Kaiming He 외

State-of-the-art visual perception models for a wide range of tasks rely on supervised pretraining. ImageNet classification is the de facto pretraining task for these models. Yet, ImageNet is now nearly ten years old and…

General Classificationimage-classificationImage Classificationobject-detection+2

Multimodal Semi-Supervised Learning for Text Recognition

2022-05-08 · Aviad Aberdam, Roy Ganz, Shai Mazor, Ron Litman

Until recently, the number of public real-world text images was insufficient for training scene text recognizers. Therefore, most modern training methods rely on synthetic data and operate in a fully supervised manner. N…

Language ModellingRepresentation LearningScene Text RecognitionSelf-Supervised Learning

MAF: Multimodal Alignment Framework for Weakly-Supervised Phrase Grounding

2020-10-12 · EMNLP 2020 11 · Qinxin Wang, Hao Tan, Sheng Shen, Michael W. Mahoney 외

Phrase localization is a task that studies the mapping from textual phrases to regions of an image. Given difficulties in annotating phrase-to-object datasets at scale, we develop a Multimodal Alignment Framework (MAF) t…

Phrase Grounding

RIVA: A Pre-trained Tweet Multimodal Model Based on Text-image Relation for Multimodal NER

2020-12-01 · COLING 2020 8 · Lin Sun, Jiquan Wang, Yindu Su, Fangsheng Weng 외

Multimodal named entity recognition (MNER) for tweets has received increasing attention recently. Most of the multimodal methods used attention mechanisms to capture the text-related visual information. However, unrelate…

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER+2