AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks

Xiao Han, Xiatian Zhu, Licheng Yu, Li Zhang, Yi-Zhe Song, Tao Xiang

CVPR 2023 · Vision-language and multimodal › Cross-modal learning · approach: Contrastive vision-language alignment · 51 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
Use one multi-task FAME-ViL model instead of its independently trained single-task versionFAME-ViL · FashionGen XMR (random 100)Mean R@K: 82.61 -> 83.14Improved
Use one multi-task FAME-ViL model instead of its independently trained single-task versionFAME-ViL · FashionIQ TGIRMean R@K: 55.36 -> 58.29Improved
Add TSA to the MTL model (ablation)CLIP-based MTL · Four-task averageAverage per-task relative performance: -5.59 -> +0.71Improved
Add XAA alone to the MTL model (ablation)CLIP-based MTL · Four-task averageAverage per-task relative performance: -5.59 -> -0.72Hurt
Add both TSA and XAA to MTL (ablation)CLIP-based MTL · Four-task averageAverage per-task relative performance: -5.59 -> +3.56Improved
Add multi-teacher distillation to MTL with TSA and XAA (ablation)CLIP-based MTL · Four-task averageAverage per-task relative performance: +3.56 -> +5.50Improved
Replace size-proportional task sampling with uniform sampling (ablation)FAME-ViL training · Four-task averageAverage per-task relative performance: +5.50 -> +3.99Hurt
Replace size-proportional task sampling with round-robin sampling (ablation)FAME-ViL training · Four-task averageAverage per-task relative performance: +5.50 -> +4.00Hurt
Use IAS instead of MTD for task balancing (ablation)Base MTL · Four-task averageAverage per-task relative performance: +5.50 -> +2.74Hurt
Add MTD to MTL with IAS (ablation)Base MTL + IAS · Four-task averageAverage per-task relative performance: +2.74 -> +5.30Improved
Use IMTLG instead of MTD for task balancing (ablation)Base MTL · Four-task averageAverage per-task relative performance: +5.50 -> -6.33Hurt
Add MTD to MTL with IMTLG (ablation)Base MTL + IMTLG · Four-task averageAverage per-task relative performance: -6.33 -> +0.44Improved

Later papers that compared with this method

2 later accepted papers report FAME-ViL as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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