Aller au contenu
Atlas de l'IA

Compréhension d’images et VQA

Regarder une image et répondre à des questions libres

Compréhension visuelleDébutant #17
entréeImageTexteTexte

Le texte intégral est présenté en anglais ; le titre et le résumé sont localisés.

CE QUE DÉSIGNE CETTE CAPACITÉ

Takes an image, optionally with a text question, and outputs a natural-language description or answer — what the person is doing, where the scene might be. Unlike OCR it targets meaning rather than characters, and unlike classification it answers open-ended questions instead of choosing from a fixed label set.

Comment c'est fait

The mainstream is a multimodal large model: a vision encoder splits the image into patches and encodes them as visual tokens, which are fed with text tokens into one Transformer so the language side produces the answer. Alignment training uses image-caption pairs with contrastive learning, and later instruction tuning teaches question answering. Small text and fine detail are preserved by splitting the image into higher-resolution patches.

Produits représentatifs

9

Organisations concernées

Usages typiques

  • Accessibility and image narration
  • Product and listing description from photos
  • Assisted reading of industrial and medical images
  • Photo management and content search

Comment on l'évalue

VQA accuracy
Share answered correctly on annotated question sets
Captioning CIDEr / SPICE
Semantic match between captions and references
Hallucination rate
Share of captions mentioning objects not in the image

Limites et points difficiles

  • Exact counting and spatial relations are unreliable; miscounting people and flipping left-right are common
  • Small text, chart readings and dense tables in the image are frequently misread
  • The model fills gaps with common sense, describing what should be there as if it were seen

Concepts sous-jacents