AI Paper Atlas

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

VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation

Chuang Gan, Yandong Li, Haoxiang Li, Chen Sun, Boqing Gong

ICCV 2017 · Vision-language and multimodal › Visual question answering · approach: Universal VQA models · 124 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 learned supervised attention featuresMLP + ResNet · VQA Real Multiple Choice test-devaccuracy: 67.4 -> 68.9Improved
add learned supervised attention featuresMLP + Attri. · VQA Real Multiple Choice test-devaccuracy: 68.4 -> 69.5Improved
replace ResNet image features with attribute featuresMLP · VQA Real Multiple Choice test-devaccuracy: 67.4 -> 68.4Improved
ensemble 10 models instead of single bestMLP + Attri. + Atten. · VQA Real Multiple Choice test-devaccuracy: 69.5 -> 70.5Improved
supervise attention with VQS segmentations instead of human attention maps (ablation)attention-augmented MLP · VQA Real MC test-dev (attention supervision comparison)accuracy (All): 68.42 -> 68.94Improved
supervise attention with VQS segmentations instead of tight bounding boxes (ablation)attention-augmented MLP · VQA Real MC test-dev (attention supervision comparison)accuracy (All): 68.65 -> 68.94Improved
add attention supervised by HAT maps (ablation)Plain MLP · VQA Real MC test-dev (attention supervision comparison)accuracy (All): 67.49 -> 68.42Improved
increase attention mask resolution from 7x7 to 14x14 (ablation)VQS attention · VQA Real MC test-dev (mask resolution)accuracy (All): 67.41 -> 68.94Improved
increase attention mask resolution from 11x11 to 14x14 (ablation)VQS attention · VQA Real MC test-dev (mask resolution)accuracy (All): 68.36 -> 68.94Improved
use word2vec embedding instead of bag-of-words for question (ablation)DeconvNet · QFSS test (14,875 questions), all typesIOU: 0.2687 -> 0.2979Improved
use LSTM embedding instead of bag-of-words for question (ablation)DeconvNet · QFSS test (14,875 questions), all typesIOU: 0.2687 -> 0.3144Improved
use word2vec embedding instead of bag-of-words for question (ablation)Mask aggregation · QFSS test (14,875 questions), all typesIOU: 0.3256 -> 0.3174Hurt

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