AI Paper Atlas

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

Differential Networks for Visual Question Answering

Chenfei Wu, Jinlai Liu, Xiaojie Wang, Ruifan Li

AAAI 2019 · Vision-language and multimodal › Visual question answering · approach: Universal VQA models · 40 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
replace fusion between feature elements (FCN-based, Mutan) with fusion of pairwise differences (DN) (ablation)DF fusion · VQA 2.0 validationaccuracy: 63.61 -> 64.89Improved
use DN on image features in addition to questions (ablation)DF · VQA 2.0 validationaccuracy: 64.46 -> 64.89Improved
use DN on question features in addition to images (ablation)DF · VQA 2.0 validationaccuracy: 64.58 -> 64.89Improved
add dropout (ablation)DF · VQA 2.0 validationaccuracy: 61.05 -> 64.89Improved
use relu instead of tanh (ablation)DF · VQA 2.0 validationaccuracy: 64.78 -> 64.89No clear effect
DF vs prior state of the art on VQA 1.0, COCO-QA, TDIUCVQA models · COCO-QA testaccuracy (All): 66.49 -> 69.36Improved
DF (36 boxes) vs Up-Down (36 boxes)VQA 2.0 · VQA 2.0 test-devaccuracy (All): 65.32 -> 67.73Improved
increase DF image features from 36 to 100 boxesDF · VQA 2.0 test-stdaccuracy (All): 67.86 -> 68.59Improved
DF vs LC Counting (100 boxes) on VQA 2.0 test-devVQA 2.0 · VQA 2.0 test-devaccuracy (All): 68.09 -> 68.31Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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