AI Paper Atlas

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

Learning Similarity Conditions Without Explicit Supervision

Reuben Tan, Mariya I. Vasileva, Kate Saenko, Bryan A. Plummer

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 94 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 dynamic condition weight branch with 5 masks instead of a single condition (ablation)SCE-Net · Polyvore Outfits valFITB accuracy (%): 53.2 -> 62.1Improved
use 5 instead of 10 condition masks (ablation)SCE-Net · Polyvore Outfits valFITB accuracy (%): 60.8 -> 62.1Improved
use 5 instead of 20 condition masks (ablation)SCE-Net · Polyvore Outfits valcompatibility AUC: 0.89 -> 0.92Improved
use SCE-Net with no test-time supervision instead of type-aware strongly supervised embeddingsoutfit compatibility · Polyvore Outfits testFITB accuracy (%): 55.3 -> 61.6Improved
use SCE-Net instead of type-aware embeddingsoutfit compatibility · Maryland Polyvore testcompatibility AUC: 0.90 -> 0.90No clear effect
use SCE-Net instead of Siamese Net on unseen categoriesfill-in-the-blank · Scarves unseen categoryFITB accuracy (%): 46.62 -> 59.46Improved
use SCE-Net instead of Siamese Net on unseen categoriesfill-in-the-blank · Accessories unseen categoryFITB accuracy (%): 50.82 -> 56.55Improved
condition weight branch on labels (text) instead of visuals (ablation)SCE-Net · Polyvore Outfits testFITB accuracy (%): 61.6 -> 60.8No clear effect
add label text features to visual features in the weight branch (ablation)SCE-Net · Polyvore Outfits testFITB accuracy (%): 61.6 -> 61.5No clear effect
use SCE-Net with 4 masks and no condition label instead of strongly supervised CSNtriplet prediction · UT-Zappos50Kerror rate (%): 10.73% -> 7.53%Improved
use 4 learned masks instead of 2 (ablation)SCE-Net · UT-Zappos50Kerror rate (%): 11.12% -> 7.53%Improved
use 200k instead of 100k training triplets (ablation)SCE-Net · UT-Zappos50Kerror rate (%): 11.37% -> 8.29%Improved

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