AI Paper Atlas

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

Inverse Visual Question Answering: A New Benchmark and VQA Diagnosis Tool

Feng Liu, Tao Xiang, Timothy M. Hospedales, Wankou Yang, Changyin Sun

TPAMI 2018 · Vision-language and multimodal › Visual question answering · approach: Universal VQA models · 31 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 the image (full iVQA model vs answer-only) (ablation)iVQA question generator · iVQA test split (VQA/COCO, question generation)ranking accuracy Acc@1 (%): 14.589 -> 30.814Improved
add the answer (full model vs image only) (ablation)iVQA question generator · iVQA test split (VQA/COCO, question generation)ranking accuracy Acc@1 (%): 13.012 -> 30.814Improved
add answer type hint to image-only VQG (ablation)VQG (I) · iVQA test split (VQA/COCO, question generation)ranking accuracy Acc@1 (%): 13.012 -> 20.277Improved
add actual answer instead of answer type (ablation)I+AT · iVQA test split (VQA/COCO, question generation)ranking accuracy Acc@1 (%): 20.277 -> 30.814Improved
re-rank VQG candidates with VQA conditioning (VQG+VQA)VQG (I) · iVQA test split (VQA/COCO, question generation)ranking accuracy Acc@1 (%): 13.012 -> 16.529Improved
use proposed variational iVQA model instead of adapted captioning SATSAT · iVQA test split (VQA/COCO, question generation)CIDEr: 1.533 -> 1.682Improved
use proposed iVQA model instead of VQG+VQAVQG+VQA · iVQA test split (VQA/COCO, question generation)ranking accuracy Acc@1 (%): 16.529 -> 30.814Improved
add image to language-only baseline in iVQAiVQA language bias baseline · iVQA test (bias gameability)acc@1 (%): 14.59 -> 28.44Improved
add image to language-only baseline in VQAVQA LSTM Q baseline · VQA test-dev (bias gameability)accuracy (%): 48.76 -> 57.75Improved
train MLB-att on balanced VQA 2.0 instead of VQA 1.0 (MLB2-att)MLB-att · VQA belief setscorrect beliefs (%): 58.8 -> 65.4Improved
train MLB-att on VQA 2.0 instead of VQA 1.0MLB-att · VQA 1.0 test-devVQA accuracy (%): 64.59 -> 62.19Hurt
add visual attention (MLB-att vs Vanilla)Vanilla VQA · VQA belief setscorrect beliefs (%): 48.6 -> 58.8Improved

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