AI Paper Atlas

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

Top-K Pairwise Ranking: Bridging the Gap Among Ranking-Based Measures for Multi-label Classification

Zitai Wang, Qianqian Xu, Zhiyong Yang, Peisong Wen, Yuan He, Xiaochun Cao, Qingming Huang

IJCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 5 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
replace ranking loss with TKPR loss (alpha2)L_rank · MS-COCO (ResNet101)mAP@3: .473 -> .752Improved
replace ranking loss with TKPR loss (alpha2)L_rank · MS-COCO (ResNet101)NDCG@3: .687 -> .813Improved
replace ranking loss with TKPR loss (alpha2)L_rank · MS-COCO (ResNet101)Ranking Loss: .034 -> .024Improved
replace best pointwise surrogate L_u4 with TKPR (alpha2)L_u4 · MS-COCO (ResNet101)mAP@3: .663 -> .752Improved
replace best pointwise surrogate L_u4 with TKPR (alpha2)L_u4 · MS-COCO (ResNet101)P@3: .615 -> .587Hurt
replace L_u4 with TKPR (alpha2)L_u4 · MS-COCO (ResNet101)Ranking Loss: .032 -> .024Improved
use alpha2 instead of alpha1 in TKPR (ablation)TKPR · MS-COCO (ResNet101)mAP@3: .730 -> .752Improved
use alpha2 instead of alpha3 in TKPR (ablation)TKPR · MS-COCO (ResNet101)NDCG@3: .782 -> .813Improved
use TKPR loss instead of ranking loss for training time (C=10,000, ResNet50)L_rank · ResNet50, C=10,000total time [s]: 0.2306 -> 0.0632Improved
use TKPR loss instead of torch.ml (C=10,000, ResNet50)torch.ml · ResNet50, C=10,000total time [s]: 0.2907 -> 0.0632Improved
use TKPR loss instead of pointwise L_u1 for time (C=10,000)L_u1 · ResNet50, C=10,000total time [s]: 0.0510 -> 0.0632No clear effect
increase classes from C=100 to C=10,000 for TKPR lossTKPR loss · ResNet50total time [s]: 0.0598 -> 0.0632No clear effect

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