AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Learning Type-Aware Embeddings for Fashion Compatibility

Mariya I. Vasileva, Bryan A. Plummer, Krishna Dusad, Shreya Rajpal, Ranjitha Kumar, David Forsyth

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 239 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
learn type-specific projections (CSN T1:1) instead of one shared embeddingSiameseNet · Maryland Polyvore (category-aware negatives)FITB accuracy: 54.4 -> 57.9Improved
add visual-semantic embedding (VSE) and similarity (Sim) constraints (ablation)CSN T1:1 · Maryland Polyvore (category-aware negatives)FITB accuracy: 57.9 -> 59.0Improved
add learned generalized distance metric (ablation)CSN T1:1 + VSE + Sim · Maryland Polyvore (category-aware negatives)FITB accuracy: 59.0 -> 61.0Improved
increase embedding size from 64-D to 512-D (ablation)CSN T1:1 + VSE + Sim + Metric · Maryland Polyvore (category-aware negatives)FITB accuracy: 61.0 -> 65.0Improved
reduce embedding size from 64-D to 32-D (ablation)CSN T1:1 + VSE + Sim + Metric · Maryland Polyvore (category-aware negatives)FITB accuracy: 61.0 -> 55.7Hurt
type-specific projections without VSE/Sim/Metric under random negativesSiameseNet · Maryland Polyvore (all negatives)FITB accuracy: 54.2 -> 51.6Hurt
add learned metric on top of VSE and Sim under random negatives (ablation)CSN T1:1 · Maryland Polyvore (all negatives)FITB accuracy: 51.5 -> 86.1Improved
share each projection across four type pairs (T4:1) instead of one per pair (ablation)CSN + VSE + Sim + Metric · Polyvore OutfitsFITB accuracy: 55.3 -> 55.1Hurt
type-specific projections instead of single embeddingSiameseNet · Polyvore OutfitsCompat. AUC: 0.81 -> 0.83Improved
use cosine distance instead of learned metric (ablation)CSN T1:1 + VSE + Sim · Polyvore OutfitsFITB accuracy: 55.3 -> 54.8Hurt
use fully connected projection instead of diagonal projection (ablation)CSN T1:1 + VSE + Sim + Metric · Polyvore OutfitsFITB accuracy: 55.3 -> 56.6Improved
increase embedding size from 32-D to 512-D (ablation)CSN T1:1 + VSE + Sim + Metric · Polyvore Outfits-DFITB accuracy: 53.2 -> 55.2Improved

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