mlsanityData to 7 Oct 2026

Pythia v0.1: the Winning Entry to the VQA Challenge 2018

arXiv 1807.09956 ↗First posted 26 Jul 2018cs.CVcited by 62

Not on the map. Why?

Abstract (arXiv)

This document describes Pythia v0.1, the winning entry from Facebook AI Research (FAIR)'s A-STAR team to the VQA Challenge 2018. Our starting point is a modular re-implementation of the bottom-up top-down (up-down) model. We demonstrate that by making subtle but important changes to the model architecture and the learning rate schedule, fine-tuning image features, and adding data augmentation, we can significantly improve the performance of the up-down model on VQA v2.0 dataset -- from 65.67% to 70.22%. Furthermore, by using a diverse ensemble of models trained with different features and on different datasets, we are able to significantly improve over the 'standard' way of ensembling (i.e. same model with different random seeds) by 1.31%. Overall, we achieve 72.27% on the test-std split of the VQA v2.0 dataset. Our code in its entirety (training, evaluation, data-augmentation, ensembling) and pre-trained models are publicly available at: https://github.com/facebookresearch/pythia

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 20; 2023: 7; 2024: 8; 2025: 1; 2026: 1.

62 papers.

Sort:

By area:

  1. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,224
  2. 2022A-OKVQA: A Benchmark for Visual Question Answering using World Knowledgecited by 702
  3. 2021How Much Can CLIP Benefit Vision-and-Language Tasks?cited by 321
  4. 2022From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Modelscited by 114
  5. 2022PromptCap: Prompt-Guided Task-Aware Image Captioningcited by 104
  6. 2022Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectlycited by 86
  7. 2021Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Modelscited by 74
  8. 2021LaTr: Layout-Aware Transformer for Scene-Text VQAcited by 72
  9. 2021Kaleido-BERT: Vision-Language Pre-training on Fashion Domaincited by 67
  10. 2022All You May Need for VQA are Image Captionscited by 65
  11. 2021Human-Adversarial Visual Question Answeringcited by 57
  12. 2022CLIPPO: Image-and-Language Understanding from Pixels Onlycited by 53
38 more
  1. 2023See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoningcited by 49
  2. 2022PreSTU: Pre-Training for Scene-Text Understandingcited by 27
  3. 2021Coarse-to-Fine Reasoning for Visual Question Answeringcited by 25
  4. 2022Toward 3D Spatial Reasoning for Human-like Text-based Visual Question Answeringcited by 24
  5. 2023Improving Selective Visual Question Answering by Learning from Your Peerscited by 24
  6. 2021Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsulescited by 22
  7. 2021Cross-Modal Retrieval Augmentation for Multi-Modal Classificationcited by 20
  8. 2021Multimodal Integration of Human-Like Attention in Visual Question Answeringcited by 20
  9. 2021LPF: A Language-Prior Feedback Objective Function for De-biased Visual Question Answeringcited by 17
  10. 2021VQA-MHUG: A Gaze Dataset to Study Multimodal Neural Attention in Visual Question Answeringcited by 16
  11. 2023Interpretable Medical Image Visual Question Answering via Multi-Modal Relationship Graph Learningcited by 16
  12. 2021Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventionscited by 15
  13. 2024Improving Generalization in Visual Reasoning via Self-Ensemblecited by 15
  14. 2021Localize, Group, and Select: Boosting Text-VQA by Scene Text Modelingcited by 14
  15. 2022VQA and Visual Reasoning: An Overview of Recent Datasets, Methods and Challengescited by 14
  16. 2022TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generationcited by 12
  17. 2021A survey on VQA_Datasets and Approachescited by 11
  18. 2023S3C: Semi-Supervised VQA Natural Language Explanation via Self-Critical Learningcited by 10
  19. 2024GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answeringcited by 9
  20. 2021Learning Better Visual Dialog Agents with Pretrained Visual-Linguistic Representationcited by 8
  21. 2022Co-VQA : Answering by Interactive Sub Question Sequencecited by 8
  22. 2024Knowledge Acquisition Disentanglement for Knowledge-based Visual Question Answering with Large Language Modelscited by 8
  23. 2021Cross-Modal Generative Augmentation for Visual Question Answeringcited by 7
  24. 2022Guiding Visual Question Answering with Attention Priorscited by 7
  25. 2022Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answeringcited by 7
  26. 2022Entity-Focused Dense Passage Retrieval for Outside-Knowledge Visual Question Answeringcited by 7
  27. 2023Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQAcited by 6
  28. 2021Understanding and Measuring Robustness of Multimodal Learningcited by 5
  29. 2022What's Different between Visual Question Answering for Machine "Understanding" Versus for Accessibility?cited by 5
  30. 2023Generating Context-Aware Natural Answers for Questions in 3D Scenescited by 5
  31. 2024Self-Bootstrapped Visual-Language Model for Knowledge Selection and Question Answeringcited by 5
  32. 2021Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answeringcited by 4
  33. 2023Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQAcited by 4
  34. 2021A Picture May Be Worth a Hundred Words for Visual Question Answeringcited by 3
  35. 2024Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World Knowledgecited by 3
  36. 2024Knowledge Condensation and Reasoning for Knowledge-based VQAcited by 3
  37. 2024Multi-Agents Based on Large Language Models for Knowledge-based Visual Question Answeringcited by 3
  38. 2021Generating and Evaluating Explanations of Attended and Error-Inducing Input Regions for VQA Modelscited by 2

50 most cited of 62 All 62 (JSON)