AI Paper Atlas

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

Identifying Ambiguous Similarity Conditions via Semantic Matching

Han-Jia Ye, Yi Shi, De-Chuan Zhan

CVPR 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 6 citations (OpenAlex)

Check 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 DiscoverNet Reg instead of LSNWS-CSL on UT-Zappos-50k with pretraining · UT-Zappos-50k, w/ pretrainGR accuracy: 76.26 -> 77.84Improved
Use DiscoverNet Reg instead of LSNWS-CSL on UT-Zappos-50k with pretraining · UT-Zappos-50k, w/ pretrainOT accuracy: 75.90 -> 77.68Improved
Use DiscoverNet Set instead of LSNWS-CSL on UT-Zappos-50k without pretraining · UT-Zappos-50k, w/o pretrainGR accuracy: 71.49 -> 74.67Improved
Use DiscoverNet Set instead of LSNWS-CSL on UT-Zappos-50k without pretraining · UT-Zappos-50k, w/o pretrainOT accuracy: 68.49 -> 74.13Improved
Use DiscoverNet Set instead of LSNWS-CSL on Celeb-A · Celeb-AGR accuracy: 70.29 -> 78.45Improved
Use DiscoverNet Set instead of LSNWS-CSL on Celeb-A · Celeb-AOT accuracy: 69.89 -> 77.98Improved
Use DiscoverNet Set instead of LSNWS-CSL on Celeb-A† · Celeb-A†GR accuracy: 57.02 -> 64.57Improved
Use DiscoverNet Set instead of LSNWS-CSL on Celeb-A† · Celeb-A†OT accuracy: 56.33 -> 63.98Improved
Increase projection count from 2 to 8 in DiscoverNet Set (ablation)DiscoverNet Set on Celeb-A with pretraining · Celeb-A, w/ pretrainOT accuracy: 77.74 -> 78.81Improved
Increase projection count from 8 to 10 in DiscoverNet Set (ablation)DiscoverNet Set on Celeb-A with pretraining · Celeb-A, w/ pretrainOT accuracy: 78.81 -> 78.68Hurt
Increase projection count from 2 to 8 in DiscoverNet Reg (ablation)DiscoverNet Reg on Celeb-A with pretraining · Celeb-A, w/ pretrainOT accuracy: 71.82 -> 74.07Improved
Increase projection count from 8 to 10 in DiscoverNet Reg (ablation)DiscoverNet Reg on Celeb-A with pretraining · Celeb-A, w/ pretrainOT accuracy: 74.07 -> 73.77Hurt

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