mlsanityData to 14 Oct 2026

Psycholinguistics meets Continual Learning: Measuring Catastrophic Forgetting in Visual Question Answering

arXiv 1906.04229 ↗First posted 10 Jun 2019cs.CLcited by 33

Not on the map. Why?

Abstract (arXiv)

We study the issue of catastrophic forgetting in the context of neural multimodal approaches to Visual Question Answering (VQA). Motivated by evidence from psycholinguistics, we devise a set of linguistically-informed VQA tasks, which differ by the types of questions involved (Wh-questions and polar questions). We test what impact task difficulty has on continual learning, and whether the order in which a child acquires question types facilitates computational models. Our results show that dramatic forgetting is at play and that task difficulty and order matter. Two well-known current continual learning methods mitigate the problem only to a limiting degree.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 9; 2023: 7; 2024: 5; 2025: 3; 2026: 3.

33 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  2. 2023Continual Pre-training of Language Modelscited by 198
  3. 2021Achieving Forgetting Prevention and Knowledge Transfer in Continual Learningcited by 91
  4. 2021Replay in Deep Learning: Current Approaches and Missing Biological Elementscited by 72
  5. 2022CLiMB: A Continual Learning Benchmark for Vision-and-Language Taskscited by 68
  6. 2023Lifelong Language Pretraining with Distribution-Specialized Expertscited by 66
  7. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  8. 2022Memory Efficient Continual Learning with Transformerscited by 43
  9. 2024Recent Advances of Multimodal Continual Learning: A Comprehensive Surveycited by 39
  10. 2022Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Taskcited by 35
  11. 2022Continual Training of Language Models for Few-Shot Learningcited by 33
  12. 2021AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Modelscited by 31
21 more
  1. 2023Machine Psychologycited by 22
  2. 2023Visual Question Answering: A Survey on Techniques and Common Trends in Recent Literaturecited by 21
  3. 2021Selective Replay Enhances Learning in Online Continual Analogical Reasoningcited by 12
  4. 2025Ask and Remember: A Questions-Only Replay Strategy for Continual Visual Question Answeringcited by 9
  5. 2022Efficient Task-Oriented Dialogue Systems with Response Selection as an Auxiliary Taskcited by 8
  6. 2023I2I: Initializing Adapters with Improvised Knowledgecited by 7
  7. 2024Enhancing Continual Learning in Visual Question Answering with Modality-Aware Feature Distillationcited by 7
  8. 2022CL-CrossVQA: A Continual Learning Benchmark for Cross-Domain Visual Question Answeringcited by 6
  9. 2024One VLM to Keep it Learning: Generation and Balancing for Data-free Continual Visual Question Answeringcited by 6
  10. 2022Task Formulation Matters When Learning Continually: A Case Study in Visual Question Answeringcited by 4
  11. 2023Visually Grounded Continual Language Learning with Selective Specializationcited by 4
  12. 2025Affordance-First Decomposition for Continual Learning in Video-Language Understandingcited by 4
  13. 2024HOP to the Next Tasks and Domains for Continual Learning in NLPcited by 3
  14. 2021Improving Scheduled Sampling with Elastic Weight Consolidation for Neural Machine Translationcited by 1
  15. 2022Neural Data-to-Text Generation Based on Small Datasets: Comparing the Added Value of Two Semi-Supervised Learning Approaches on Top of a Large Language Modelcited by 1
  16. 2024A look under the hood of the Interactive Deep Learning Enterprise (No-IDLE)cited by 1
  17. 2025CurLL: A Developmental Framework to Evaluate Continual Learning in Language Modelscited by 1
  18. 2026Attention-Spectrum Regularization for Replay-Free Continual Multimodal LLMscited by 1
  19. 2022Utilizing Priming to Identify Optimal Class Ordering to Alleviate Catastrophic Forgettingcited by 0
  20. 2026MacVQA: Adaptive Memory Allocation and Global Noise Filtering for Continual Visual Question Answeringcited by 0
  21. 2026HyLoVQA: Dynamic Hypernetwork-Generated Low-Rank Adaptation for Continual Visual Question Answeringcited by 0