AI Paper Atlas

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

Multi-Scale Deep Learning Architectures for Person Re-Identification

Xuelin Qian, Yanwei Fu, Yu-Gang Jiang, Tao Xiang, Xiangyang Xue

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 337 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 saliency-based learning fusion layer (ablation)MuDeep · CUHK01Rank-1 accuracy: 77.88 -> 79.01Improved
add classification subnet (ablation)MuDeep · CUHK01Rank-1 accuracy: 76.21 -> 79.01Improved
add both fusion layer and classification subnet (ablation)MuDeep · CUHK01Rank-1 accuracy: 74.21 -> 79.01Improved
use multi-scale stream layers instead of Inception A+B (ablation)MuDeep · CUHK01Rank-1 accuracy: 72.11 -> 79.01Improved
use multi-scale stream layers instead of Inception B (ablation)MuDeep · CUHK01Rank-1 accuracy: 67.31 -> 79.01Improved
use multi-scale stream layers instead of Inception A (ablation)MuDeep · CUHK01Rank-1 accuracy: 60.11 -> 79.01Improved
use gradual Reduction layer instead of max-pooling (ablation)MuDeep · CUHK01Rank-1 accuracy: more than 10% absolute points lowerImproved
use squared feature difference instead of plain difference (ablation)MuDeep verification subnet · CUHK01Rank-1 accuracy: 2.2% higherImproved
train jointly with CUHK03 labelled and detected dataMuDeep · CUHK03-DetectedRank-1 accuracy: 75.34 -> 75.64Improved
train jointly with CUHK03 labelled and detected dataMuDeep · CUHK03-LabelledRank-1 accuracy: 76.34 -> 76.87Improved
fuse models trained at original and lower resolutionMuDeep · CUHK01 / VIPeR / CUHK03Rank-1 accuracy: around 1-2% lowerHurt
add max-pooling frame aggregation for video re-id (no RNN)MuDeep · PRID-2011Rank-1 accuracy: 65 vs 70 (RCNvrid)Mixed

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