AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Learning to Count Objects in Natural Images for Visual Question Answering

Yan Zhang, Jonathon Hare, Adam Prügel-Bennett

ICLR 2018 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 196 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add differentiable counting from object proposals to the VQA baselineVQA baseline · VQA v2 test-devNumber accuracy: 46.88 -> 51.62Improved
Add differentiable counting from object proposals to the VQA baselineVQA baseline · VQA v2 testNumber accuracy: 46.60 -> 51.39Improved
Add differentiable counting from object proposals to the VQA baselineVQA baseline · VQA v2 validationNumber accuracy: 44.83$\pm$0.2 -> 49.36$\pm$0.1Improved
Add differentiable counting from object proposals to the VQA baselineVQA baseline · VQA v2 validation, how-many questionsCount accuracy: 51.69$\pm$0.2 -> 57.03$\pm$0.0Improved
Add differentiable counting from object proposals to the VQA baselineVQA baseline · VQA v2 validationBalanced pair accuracy, Number: 17.34$\pm$0.2 -> 23.10$\pm$0.2Improved
Add differentiable counting from object proposals to the VQA baselineVQA baseline · VQA v2 validation, how-many questionsBalanced pair accuracy, Count: 20.02$\pm$0.2 -> 26.63$\pm$0.2Improved
Replace the differentiable counting module with non-maximum suppression (ablation)VQA baseline · VQA v2 validationNumber accuracy: 44.83$\pm$0.2 -> 44.60$\pm$0.1Hurt
Replace the differentiable counting module with non-maximum suppression (ablation)VQA baseline · VQA v2 validation, how-many questionsCount accuracy: 51.69$\pm$0.2 -> 51.41$\pm$0.1Hurt
Replace the differentiable counting module with non-maximum suppression (ablation)VQA baseline · VQA v2 validationBalanced pair accuracy, Number: 17.34$\pm$0.2 -> 17.06$\pm$0.1Hurt
Replace the differentiable counting module with non-maximum suppression (ablation)VQA baseline · VQA v2 validation, how-many questionsBalanced pair accuracy, Count: 20.02$\pm$0.2 -> 19.72$\pm$0.1Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy