mlsanityData to 7 Oct 2026

Learning to Count Objects in Natural Images for Visual Question Answering

arXiv 1802.05766 ↗First posted 15 Feb 2018cs.CV cs.CLcited by 40

Not on the map. Why?

Abstract (arXiv)

Visual Question Answering (VQA) models have struggled with counting objects in natural images so far. We identify a fundamental problem due to soft attention in these models as a cause. To circumvent this problem, we propose a neural network component that allows robust counting from object proposals. Experiments on a toy task show the effectiveness of this component and we obtain state-of-the-art accuracy on the number category of the VQA v2 dataset without negatively affecting other categories, even outperforming ensemble models with our single model. On a difficult balanced pair metric, the component gives a substantial improvement in counting over a strong baseline by 6.6%.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 10; 2023: 6; 2024: 6; 2025: 3; 2026: 5.

40 papers.

Sort:

By area:

  1. 2023NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenariocited by 258
  2. 2023Teaching CLIP to Count to Tencited by 194
  3. 2021Causal Attention for Vision-Language Taskscited by 111
  4. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 50
  5. 2022From Easy to Hard: Learning Language-guided Curriculum for Visual Question Answering on Remote Sensing Datacited by 38
  6. 2022MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answeringcited by 36
  7. 2021Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generationcited by 35
  8. 2023Behind the Magic, MERLIM: Multi-modal Evaluation Benchmark for Large Image-Language Modelscited by 23
  9. 2022Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semanticscited by 22
  10. 2022On Modality Bias Recognition and Reductioncited by 20
  11. 2021AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Losscited by 18
  12. 2021BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generationcited by 18
28 more
  1. 2022Visual Perturbation-aware Collaborative Learning for Overcoming the Language Prior Problemcited by 18
  2. 2021VQA-MHUG: A Gaze Dataset to Study Multimodal Neural Attention in Visual Question Answeringcited by 16
  3. 2023On the Promises and Challenges of Multimodal Foundation Models for Geographical, Environmental, Agricultural, and Urban Planning Applicationscited by 15
  4. 2022VQA and Visual Reasoning: An Overview of Recent Datasets, Methods and Challengescited by 14
  5. 2024A Comprehensive Survey on Visual Question Answering Datasets and Algorithmscited by 8
  6. 2022Guiding Visual Question Answering with Attention Priorscited by 7
  7. 2022Semantic-aware Modular Capsule Routing for Visual Question Answeringcited by 5
  8. 2024Visual Enumeration Remains Challenging for Multimodal Generative AIcited by 5
  9. 2025Emergent Symbol-like Number Variables in Artificial Neural Networkscited by 5
  10. 2021Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answeringcited by 4
  11. 2024Detection-Driven Object Count Optimization for Text-to-Image Diffusion Modelscited by 4
  12. 2024QUOTA: Quantifying Objects with Text-to-Image Models for Any Domaincited by 3
  13. 2026UNICBench: UNIfied Counting Benchmark for MLLMcited by 3
  14. 2021HySTER: A Hybrid Spatio-Temporal Event Reasonercited by 2
  15. 2021Visual Question Answering based on Local-Scene-Aware Referring Expression Generationcited by 2
  16. 2022MGA-VQA: Multi-Granularity Alignment for Visual Question Answeringcited by 2
  17. 2023Object Attribute Matters in Visual Question Answeringcited by 2
  18. 2024Quantity Matters: Towards Assessing and Mitigating Number Hallucination in Large Vision-Language Modelscited by 2
  19. 2025What is the Right Embedding Space for Contrastive Learning in Referring Expression Counting?cited by 2
  20. 2021Analysis on Image Set Visual Question Answeringcited by 1
  21. 2025Assessing the Visual Enumeration Abilities of Specialized Counting Architectures and Vision-Language Modelscited by 1
  22. 2026The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Countingcited by 1
  23. 2022SA-VQA: Structured Alignment of Visual and Semantic Representations for Visual Question Answeringcited by 0
  24. 2023Understanding and Mitigating Classification Errors Through Interpretable Token Patternscited by 0
  25. 2024Enhanced Textual Feature Extraction for Visual Question Answering: A Simple Convolutional Approachcited by 0
  26. 2026OneCanvas: 3D Scene Understanding via Panoramic Reprojectioncited by 0
  27. 2026HoloCount: A Holistic Visual Counting Benchmark for MLLMscited by 0
  28. 2026Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Modelscited by 0