AI Paper Atlas

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

Group Re-Identification via Unsupervised Transfer of Sparse Features Encoding

Giuseppe Lisanti, Niki Martinel, Alberto Del Bimbo, Gian Luca Foresti

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 59 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 average pooling instead of max pooling of cosine residuals (ablation)PREF (500 atoms, E+V+C) · i-LIDS groupsRank-1 accuracy: 24.6 -> 31.1Improved
use cosine instead of Euclidean residual distance (average pooling) (ablation)PREF (500 atoms, E+V+C) · i-LIDS groupsRank-1 accuracy: 28.5 -> 31.1Improved
use cosine instead of L1 distance (average pooling) (ablation)PREF (500 atoms, E+V+C) · i-LIDS groupsRank-1 accuracy: 30.1 -> 31.1Improved
train dictionary on ETHZ, VIPeR and CAVIAR instead of CAVIAR only (cosine, average) (ablation)PREF (500 atoms) · i-LIDS groupsRank-1 accuracy: 29.6 -> 31.1Improved
train dictionary on ETHZ+VIPeR+CAVIAR instead of ETHZ only (cosine, average) (ablation)PREF (500 atoms) · i-LIDS groupsRank-1 accuracy: 31.2 -> 31.1No clear effect
increase PCA components from 20 to 50 (ablation)PREF (500 atoms) · i-LIDS groupsRank-1 accuracy: 29.4 -> 31.1No clear effect
use 500 atoms instead of 300 (ablation)PREF · i-LIDS groupsRank-1 accuracy: 29.3 -> 31.1Improved
use 1000 atoms instead of 500 (ablation)PREF · OGRERank-1 accuracy: 15.1 -> 12.9Hurt
replace IFV (128 clusters) with PREF (500 atoms)encoding · i-LIDS groupsRank-1 accuracy: 26.1 -> 31.1Improved
replace VLAD (500) with PREF (500)encoding · Museum groupsRank-1 accuracy: 23.0 -> 25.8Improved
replace IFV (64 clusters) with PREF (500 atoms)encoding · OGRERank-1 accuracy: 14.6 -> 15.1Improved
concatenate (x,y) patch position to features (ablation)PREF (500 atoms) · i-LIDS groupsRank-1 accuracy: 31.1 -> 21.7Hurt

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