mlsanityData to 7 Oct 2026

Learning by Asking Questions

arXiv 1712.01238 ↗First posted 4 Dec 2017cs.CV cs.CL cs.LGcited by 25

Not on the map. Why?

Abstract (arXiv)

We introduce an interactive learning framework for the development and testing of intelligent visual systems, called learning-by-asking (LBA). We explore LBA in context of the Visual Question Answering (VQA) task. LBA differs from standard VQA training in that most questions are not observed during training time, and the learner must ask questions it wants answers to. Thus, LBA more closely mimics natural learning and has the potential to be more data-efficient than the traditional VQA setting. We present a model that performs LBA on the CLEVR dataset, and show that it automatically discovers an easy-to-hard curriculum when learning interactively from an oracle. Our LBA generated data consistently matches or outperforms the CLEVR train data and is more sample efficient. We also show that our model asks questions that generalize to state-of-the-art VQA models and to novel test time distributions.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 6; 2023: 3; 2024: 5; 2025: 4.

25 papers.

Sort:

By area:

  1. 2021Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answeringcited by 62
  2. 2021Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Languagecited by 55
  3. 2022Learning to Execute Actions or Ask Clarification Questionscited by 30
  4. 2024LOVA3: Learning to Visual Question Answering, Asking and Assessmentcited by 21
  5. 2021Open-domain clarification question generation without question examplescited by 20
  6. 2022Learning to Retrieve Videos by Asking Questionscited by 17
  7. 2024Right this way: Can VLMs Guide Us to See More to Answer Questions?cited by 10
  8. 2022K-VQG: Knowledge-aware Visual Question Generation for Common-sense Acquisitioncited by 9
  9. 2021Single-Modal Entropy based Active Learning for Visual Question Answeringcited by 6
  10. 2025From Pixels to Graphs: using Scene and Knowledge Graphs for HD-EPIC VQA Challengecited by 6
  11. 2021KANDINSKYPatterns -- An experimental exploration environment for Pattern Analysis and Machine Intelligencecited by 5
  12. 2022Look, Read and Ask: Learning to Ask Questions by Reading Text in Imagescited by 5
13 more
  1. 2021Field-Guide-Inspired Zero-Shot Learningcited by 4
  2. 2023From Wrong To Right: A Recursive Approach Towards Vision-Language Explanationcited by 4
  3. 2023Learning to Explore Informative Trajectories and Samples for Embodied Perceptioncited by 3
  4. 2025Learning What Matters: Prioritized Concept Learning via Relative Error-driven Sample Selectioncited by 3
  5. 2022Learning by Asking Questions for Knowledge-based Novel Object Recognitioncited by 2
  6. 2024Advancing Large Multi-modal Models with Explicit Chain-of-Reasoning and Visual Question Generationcited by 2
  7. 2024Diagram-Driven Course Questions Generationcited by 2
  8. 2022Ask Before You Act: Generalising to Novel Environments by Asking Questionscited by 1
  9. 2024CAUS: A Dataset for Question Generation based on Human Cognition Leveraging Large Language Modelscited by 1
  10. 2025Long-context Non-factoid Question Answering in Indic Languagescited by 1
  11. 2021Meaning Versus Information, Prediction Versus Memory, and Question Versus Answercited by 0
  12. 2023Weakly Supervised Visual Question Answer Generationcited by 0
  13. 2025Active Learning Methods for Efficient Data Utilization and Model Performance Enhancementcited by 0