AI Paper Atlas

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

Creating Training Sets via Weak Indirect Supervision

Jieyu Zhang, Bohan Wang, Xiangchen Song, Yujing Wang, Yaming Yang, Jing Bai, Alexander Ratner

ICLR 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 3 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
Model ILF accuracy and fine-grained label-relation strengths explicitly instead of using pseudo-accuracy factorsWS-LG / PLRM · LSHTC-3, label modelAccuracy: 62.60 $\pm$ { 10.12} -> 64.65 $\pm$ { 11.30}Improved
Model ILF accuracy and fine-grained label-relation strengths explicitly instead of using pseudo-accuracy factorsWS-LG / PLRM · LSHTC-3, end modelF1-score: 67.36 $\pm$ { 14.24} -> 69.37 $\pm$ { 14.41}Improved
Model ILF accuracy and fine-grained label-relation strengths explicitly instead of using pseudo-accuracy factorsWS-LG / PLRM · ILSVRC2012, label modelAccuracy: 53.68 $\pm$ { 7.62} -> 56.18 $\pm$ { 7.35}Improved
Model ILF accuracy and fine-grained label-relation strengths explicitly instead of using pseudo-accuracy factorsWS-LG / PLRM · ILSVRC2012, end modelF1-score: 54.57 $\pm$ { 11.17} -> 56.83 $\pm$ { 8.49}Improved
Use PLRM rather than WS-LG to synthesize labelsPLRM · Car AccessoriesF1: 66.85 -> 76.37Improved
Use PLRM rather than WS-LG to synthesize labelsPLRM · Car AccessoriesAccuracy: 66.33 -> 75.83Improved
Use PLRM rather than WS-LG to synthesize labelsPLRM · FurnitureF1: 70.59 -> 80.57Improved
Use PLRM rather than WS-LG to synthesize labelsPLRM · FurnitureAccuracy: 74.51 -> 82.02Improved
Violate the distinguishability condition by giving unseen labels identical relations to every seen labelPLRM · WIS tasks with indistinguishable unseen labelsOverall performance: about 10 pointsHurt

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