AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Adaptive Offline Quintuplet Loss for Image-Text Matching

Tianlang Chen, Jiajun Deng, Jiebo Luo

ECCV 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Multimodal retrieval-augmented modeling · 77 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
train with offline hard negatives and adaptive offline quintuplet lossBFAN · MS-COCO 5K testsentence retrieval R@1: 52.9 -> 57.3Improved
train with AdapOffQuinVSRN · MS-COCO 1K testrsum: 516.8 -> 521.4Improved
train with AdapOffQuinSCAN · MS-COCO 1K testrsum: 507.9 -> 511.2Improved
train with AdapOffQuinBFAN · Flickr30K 1K testrsum: 470.4 -> 486.7Improved
add offline quintuplet (derived non-shared-anchor negative pairs) to offline triplet loss (ablation)BFAN · MS-COCO 1K testrsum: 513.4 -> 514.7Improved
add adaptive hierarchical penalization to offline quintuplet loss (ablation)BFAN · MS-COCO 1K testrsum: 514.7 -> 517.2Improved
add offline triplet loss to online triplet loss (ablation)VSRN · MS-COCO 1K testrsum: 516.8 -> 518.6Improved
keep online loss term alongside offline negatives instead of only offline (ablation)VSRN · MS-COCO 1K testsentence retrieval R@1: 0.7 -> 77.5Improved
retrain from scratch in second round instead of fine-tuning (ablation)VSRN · MS-COCO 1K testsentence retrieval R@1: 74.5 -> 77.5Improved
derive extra negative pairs from offline instead of online negatives (ablation)BFAN · MS-COCO 1K testsentence retrieval R@1: 75.3 -> 77.3Improved
add offline-negative scores into online term for hierarchy (ablation)VSRN · MS-COCO 1K testsentence retrieval R@1: 77.1 -> 77.5Improved
vary top list size h from 200 to 1000 (ablation)VSRN · MS-COCO 1K testsentence retrieval R@1: 77.1 -> 77.3No clear effect

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