AI Paper Atlas

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

SPL-MLL: Selecting Predictable Landmarks for Multi-Label Learning

Junbing Li, Changqing Zhang, Pengfei Zhu, Baoyuan Wu, Lei Chen, Qinghua Hu

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 12 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
add landmark selection and landmark prediction on top of NN embeddings (ablation)NN-embeddings · pascal VOC 2007Average Precision: 0.431 -> 0.616Improved
add landmark selection and landmark prediction on top of NN embeddings (ablation)NN-embeddings · pascal VOC 2007Micro-F1: 0.308 -> 0.586Improved
learn landmark selection and prediction jointly instead of separately (ablation)Ours (NN + separated) · pascal VOC 2007Average Precision: 0.521 -> 0.616Improved
learn landmark selection and prediction jointly instead of separately (ablation)Ours (NN + separated) · pascal VOC 2007Micro-F1: 0.384 -> 0.586Improved
learn landmark selection and prediction jointly instead of separately (ablation)Ours (NN + separated) · pascal VOC 2007Ranking Loss: 0.243 -> 0.184Improved
use neural network embedding instead of linear projection (ablation)Ours (joint + linear) · pascal VOC 2007Micro-F1: 0.516 -> 0.586Improved
use neural network embedding instead of linear projection (ablation)Ours (joint + linear) · pascal VOC 2007Average Precision: 0.608 -> 0.616Improved
use neural network embedding instead of linear projection (ablation)Ours (linear) · emotionsAverage Precision: 0.798 -> 0.815Improved
use neural network embedding instead of linear projection (ablation)Ours (linear) · sceneAverage Precision: 0.861 -> 0.884Improved
use neural network embedding instead of linear projection (ablation)Ours (linear) · tmc2007Micro-F1: 0.912 -> 0.944Improved
use neural network embedding instead of linear projection (ablation)Ours (linear) · espgameAverage Precision: 0.289 -> 0.291No clear effect
add joint landmark selection over linear label-space baselines (2-step landmark methods) (ablation)ML-CSSP · tmc2007Micro-F1: 0.604 -> 0.944Improved

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