# PV2TEA: Patching Visual Modality to Textual-Established Information Extraction

arXiv: https://arxiv.org/abs/2306.01016 · HTML: https://mlsanity.com/paper/2306.01016/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 40 references that are in the map.
- First posted on arXiv 1 Jun 2023.

## Builds on (most cited first, 30 of 32)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [SimVLM: Simple Visual Language Model Pretraining with Weak Supervision](https://mlsanity.com/paper/2108.10904/) (2021)
- [Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks](https://mlsanity.com/paper/2208.10442/) (2022)
- [Noise or Signal: The Role of Image Backgrounds in Object Recognition](https://mlsanity.com/paper/2006.09994/) (2020)
- [Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach](https://mlsanity.com/paper/2010.07835/) (2020)
- [OpenTag: Open Attribute Value Extraction from Product Profiles [Deep Learning, Active Learning, Named Entity Recognition]](https://mlsanity.com/paper/1806.01264/) (2018)
- [Optimizing Relevance Maps of Vision Transformers Improves Robustness](https://mlsanity.com/paper/2206.01161/) (2022)
- [Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product](https://mlsanity.com/paper/2009.07162/) (2020)
- [Putting visual object recognition in context](https://mlsanity.com/paper/1911.07349/) (2019)
- [AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding](https://mlsanity.com/paper/2106.02318/) (2021)
- [TXtract: Taxonomy-Aware Knowledge Extraction for Thousands of Product Categories](https://mlsanity.com/paper/2004.13852/) (2020)
- [Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integration](https://mlsanity.com/paper/2107.05080/) (2021)
- [Training Subset Selection for Weak Supervision](https://mlsanity.com/paper/2206.02914/) (2022)
- [PAM: Understanding Product Images in Cross Product Category Attribute Extraction](https://mlsanity.com/paper/2106.04630/) (2021)

## Built on by (most cited first, 2 of 2)

- [Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting](https://mlsanity.com/paper/2310.18804/) (2023)
- [VIKSER: Visual Knowledge-Driven Self-Reinforcing Reasoning Framework](https://mlsanity.com/paper/2502.00711/) (2025)

## Abstract (arXiv)

Information extraction, e.g., attribute value extraction, has been extensively studied and formulated based only on text. However, many attributes can benefit from image-based extraction, like color, shape, pattern, among others. The visual modality has long been underutilized, mainly due to multimodal annotation difficulty. In this paper, we aim to patch the visual modality to the textual-established attribute information extractor. The cross-modality integration faces several unique challenges: (C1) images and textual descriptions are loosely paired intra-sample and inter-samples; (C2) images usually contain rich backgrounds that can mislead the prediction; (C3) weakly supervised labels from textual-established extractors are biased for multimodal training. We present PV2TEA, an encoder-decoder architecture equipped with three bias reduction schemes: (S1) Augmented label-smoothed contrast to improve the cross-modality alignment for loosely-paired image and text; (S2) Attention-pruning that adaptively distinguishes the visual foreground; (S3) Two-level neighborhood regularization that mitigates the label textual bias via reliability estimation. Empirical results on real-world e-Commerce datasets demonstrate up to 11.74% absolute (20.97% relatively) F1 increase over unimodal baselines.