# K-LITE: Learning Transferable Visual Models with External Knowledge

arXiv: https://arxiv.org/abs/2204.09222 · HTML: https://mlsanity.com/paper/2204.09222/

## Key facts

- Cited by 79 papers in the map (data through 14 Oct 2026).
- Builds on 66 of its 107 references that are in the map.
- First posted on arXiv 20 Apr 2022.

## Builds on (most cited first, 30 of 66)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [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)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)

## Built on by (most cited first, 30 of 79)

- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [Visual Classification via Description from Large Language Models](https://mlsanity.com/paper/2210.07183/) (2022)
- [Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification](https://mlsanity.com/paper/2211.11158/) (2022)
- [What does a platypus look like? Generating customized prompts for zero-shot image classification](https://mlsanity.com/paper/2209.03320/) (2022)
- [MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining](https://mlsanity.com/paper/2208.12262/) (2022)
- [Exploring scalable medical image encoders beyond text supervision](https://mlsanity.com/paper/2401.10815/) (2024)
- [Vision-Language Pre-training: Basics, Recent Advances, and Future Trends](https://mlsanity.com/paper/2210.09263/) (2022)
- [Waffling around for Performance: Visual Classification with Random Words and Broad Concepts](https://mlsanity.com/paper/2306.07282/) (2023)
- [Scaling Vision-Language Models with Sparse Mixture of Experts](https://mlsanity.com/paper/2303.07226/) (2023)
- [CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets](https://mlsanity.com/paper/2302.02551/) (2023)
- [BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data](https://mlsanity.com/paper/2402.08093/) (2024)
- [Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures](https://mlsanity.com/paper/2307.15220/) (2023)
- [Open-Set Image Tagging with Multi-Grained Text Supervision](https://mlsanity.com/paper/2310.15200/) (2023)
- [Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Study](https://mlsanity.com/paper/2209.15517/) (2022)
- [The Neglected Tails in Vision-Language Models](https://mlsanity.com/paper/2401.12425/) (2024)
- [Learning Customized Visual Models with Retrieval-Augmented Knowledge](https://mlsanity.com/paper/2301.07094/) (2023)
- [Multitask Vision-Language Prompt Tuning](https://mlsanity.com/paper/2211.11720/) (2022)
- [KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation](https://mlsanity.com/paper/2303.15796/) (2023)
- [Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs](https://mlsanity.com/paper/2305.06343/) (2023)
- [Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation](https://mlsanity.com/paper/2410.00263/) (2024)
- [Retrieval-Enhanced Contrastive Vision-Text Models](https://mlsanity.com/paper/2306.07196/) (2023)
- [CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection](https://mlsanity.com/paper/2309.01093/) (2023)
- [Language Models as Black-Box Optimizers for Vision-Language Models](https://mlsanity.com/paper/2309.05950/) (2023)
- [Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval](https://mlsanity.com/paper/2403.16005/) (2024)
- [Affective Faces for Goal-Driven Dyadic Communication](https://mlsanity.com/paper/2301.10939/) (2023)
- [Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models](https://mlsanity.com/paper/2308.11186/) (2023)
- [Doubly Right Object Recognition: A Why Prompt for Visual Rationales](https://mlsanity.com/paper/2212.06202/) (2022)
- [DIME-FM: DIstilling Multimodal and Efficient Foundation Models](https://mlsanity.com/paper/2303.18232/) (2023)
- [Few-shot Adaptation of Multi-modal Foundation Models: A Survey](https://mlsanity.com/paper/2401.01736/) (2024)

## Abstract (arXiv)

The new generation of state-of-the-art computer vision systems are trained from natural language supervision, ranging from simple object category names to descriptive captions. This form of supervision ensures high generality and usability of the learned visual models, due to the broad concept coverage achieved via large-scale data collection process. Alternatively, we argue that learning with external knowledge is a promising way which leverages a much more structured source of supervision and offers sample efficiency. We propose K-LITE, a simple strategy to leverage external knowledge for building transferable visual systems: In training, it enriches entities in text with WordNet and Wiktionary knowledge, leading to an efficient and scalable approach to learning image representations that uses knowledge about the visual concepts. In evaluation, the text is also augmented with external knowledge and then used to reference learned visual concepts (or describe new ones) to enable zero-shot and few-shot transfer of the pre-trained models. We study the performance of K-LITE on two important computer vision problems, image classification and object detection, benchmarking on 20 and 13 different existing datasets, respectively. The proposed knowledge-augmented models show significant improvement in transfer learning performance over existing methods. Our code is available at https://github.com/microsoft/klite.