AI Paper Atlas

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

Person Re-identification in Identity Regression Space

Hanxiao Wang, Xiatian Zhu, Shaogang Gong, Tao Xiang

IJCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 31 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 OneHot identity coding instead of random coding (ablation)IRS (LOMO) · Market-1501 (single-query)Rank-1 (%): 47.4 -> 57.7Improved
use OneHot identity coding instead of random coding (ablation)IRS (LOMO) · CUHK03 (manual)Rank-1 (%): 51.7 -> 61.6Improved
use OneHot coding instead of FDA coding (ablation)IRS (LOMO) · Market-1501 (single-query)Rank-1 (%): 55.6 -> 57.7Improved
use OneHot coding instead of FDA coding (ablation)IRS (LOMO) · VIPeR and CUHK01Rank-1 (%): 45.1 -> 45.1No clear effect
fuse WHOS, LOMO and CNN features by score-level fusion instead of single LOMO (ablation)IRS · VIPeRRank-1 (%): 45.1 -> 54.6Improved
fuse WHOS, LOMO and CNN features instead of CNN alone (ablation)IRS · CUHK01 (486/485 split)Rank-1 (%): 68.6 -> 80.8Improved
use CUHK03-trained CNN feature without fine-tuning instead of LOMO (ablation)IRS · VIPeRRank-1 (%): 45.1 -> 33.1Hurt
use CNN feature instead of LOMO (ablation)IRS · CUHK03 (detected)Rank-1 (%): 53.4 -> 80.3Improved
use CNN feature instead of LOMO (ablation)IRS · Market-1501 (single-query)Rank-1 (%): 57.7 -> 72.7Improved
add IRS regression with 2 FC layers on top of DGD CNN features (ablation)DGD · CUHK03 (manual)Rank-1 (%): 73.7 -> 76.6Improved
use 3 FC layers instead of 2 in deep learning regression (ablation)IRS (DLR) · CUHK03 (manual)Rank-1 (%): 76.6 -> 74.2Hurt
use ridge regression instead of deep learning regression (ablation)IRS · CUHK03 (manual)Rank-1 (%): 76.6 -> 81.5Improved

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