# Webly Supervised Concept Expansion for General Purpose Vision Models

arXiv: https://arxiv.org/abs/2202.02317 · HTML: https://mlsanity.com/paper/2202.02317/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 98 references that are in the map.
- First posted on arXiv 4 Feb 2022.

## Builds on (most cited first, 30 of 56)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [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)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [nocaps: novel object captioning at scale](https://mlsanity.com/paper/1812.08658/) (2018)
- [Open-Vocabulary Object Detection Using Captions](https://mlsanity.com/paper/2011.10678/) (2020)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [Unifying Vision-and-Language Tasks via Text Generation](https://mlsanity.com/paper/2102.02779/) (2021)

## Built on by (most cited first, 30 of 45)

- [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://mlsanity.com/paper/2206.01718/) (2022)
- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks](https://mlsanity.com/paper/2206.08916/) (2022)
- [Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action](https://mlsanity.com/paper/2312.17172/) (2023)
- [SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding](https://mlsanity.com/paper/2211.15660/) (2022)
- [REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory](https://mlsanity.com/paper/2212.05221/) (2022)
- [Vision-Language Pre-training: Basics, Recent Advances, and Future Trends](https://mlsanity.com/paper/2210.09263/) (2022)
- [From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models](https://mlsanity.com/paper/2212.10846/) (2022)
- [PromptCap: Prompt-Guided Task-Aware Image Captioning](https://mlsanity.com/paper/2211.09699/) (2022)
- [AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn](https://mlsanity.com/paper/2306.08640/) (2023)
- [PerceptionGPT: Effectively Fusing Visual Perception into LLM](https://mlsanity.com/paper/2311.06612/) (2023)
- [Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks](https://mlsanity.com/paper/2211.09808/) (2022)
- [LAVIS: A Library for Language-Vision Intelligence](https://mlsanity.com/paper/2209.09019/) (2022)
- [See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning](https://mlsanity.com/paper/2301.05226/) (2023)
- [IdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language Models](https://mlsanity.com/paper/2305.14985/) (2023)
- [Text encoders bottleneck compositionality in contrastive vision-language models](https://mlsanity.com/paper/2305.14897/) (2023)
- [GRIT: General Robust Image Task Benchmark](https://mlsanity.com/paper/2204.13653/) (2022)
- [I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision](https://mlsanity.com/paper/2211.09778/) (2022)
- [DesCo: Learning Object Recognition with Rich Language Descriptions](https://mlsanity.com/paper/2306.14060/) (2023)
- [Internet Explorer: Targeted Representation Learning on the Open Web](https://mlsanity.com/paper/2302.14051/) (2023)
- [VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge](https://mlsanity.com/paper/2210.13626/) (2022)
- [Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!](https://mlsanity.com/paper/2306.03932/) (2023)
- [Improving Generalization in Visual Reasoning via Self-Ensemble](https://mlsanity.com/paper/2410.20883/) (2024)
- [Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning](https://mlsanity.com/paper/2405.20834/) (2024)
- [ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation](https://mlsanity.com/paper/2311.13258/) (2023)
- [ViCor: Bridging Visual Understanding and Commonsense Reasoning with Large Language Models](https://mlsanity.com/paper/2310.05872/) (2023)
- [Training Vision-Language Transformers from Captions](https://mlsanity.com/paper/2205.09256/) (2022)
- [Genixer: Empowering Multimodal Large Language Models as a Powerful Data Generator](https://mlsanity.com/paper/2312.06731/) (2023)
- [GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering](https://mlsanity.com/paper/2402.02503/) (2024)
- [Rationale-guided Prompting for Knowledge-based Visual Question Answering](https://mlsanity.com/paper/2412.16936/) (2024)

## Abstract (arXiv)

General Purpose Vision (GPV) systems are models that are designed to solve a wide array of visual tasks without requiring architectural changes. Today, GPVs primarily learn both skills and concepts from large fully supervised datasets. Scaling GPVs to tens of thousands of concepts by acquiring data to learn each concept for every skill quickly becomes prohibitive. This work presents an effective and inexpensive alternative: learn skills from supervised datasets, learn concepts from web image search, and leverage a key characteristic of GPVs: the ability to transfer visual knowledge across skills. We use a dataset of 1M+ images spanning 10k+ visual concepts to demonstrate webly-supervised concept expansion for two existing GPVs (GPV-1 and VL-T5) on 3 benchmarks: 5 COCO-based datasets (80 primary concepts), a newly curated series of 5 datasets based on the OpenImages and VisualGenome repositories (~500 concepts), and the Web-derived dataset (10k+ concepts). We also propose a new architecture, GPV-2 that supports a variety of tasks -- from vision tasks like classification and localization to vision+language tasks like QA and captioning, to more niche ones like human-object interaction detection. GPV-2 benefits hugely from web data and outperforms GPV-1 and VL-T5 across these benchmarks. Our data, code, and web demo are available at https://prior.allenai.org/projects/gpv2.