AI Paper Atlas

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

Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification

Yu-Jhe Li, Yun-Chun Chen, Yen-Yu Lin, Xiaofei Du, Yu-Chiang Frank Wang

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 100 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 image-level adversarial loss (ablation)CRGAN · MLR-CUHK03 (ablation)Rank-1 (%): 82.1 -> 79.8 without itImproved
add image-level adversarial loss (ablation)CRGAN · MLR-CUHK03 (ablation)LPIPS: 0.07 -> 0.17 without itImproved
add feature-level adversarial loss (ablation)CRGAN · MLR-CUHK03 (ablation)Rank-1 (%): 82.1 -> 67.6 without itImproved
add HR reconstruction loss (ablation)CRGAN · MLR-CUHK03 (ablation)Rank-1 (%): 82.1 -> 66.7 without itImproved
add classification loss (ablation)CRGAN · MLR-CUHK03 (ablation)Rank-1 (%): 82.1 -> 1.7 without itImproved
add classification loss (ablation)CRGAN · MLR-CUHK03 (ablation)PSNR: 20.2 -> 21.4 without itHurt
use joint representation [f,g] instead of f only (ablation)CRGAN · MLR-CUHK03Rank-1 (%): 77.6 -> 82.1Improved
use joint representation [f,g] instead of g only (ablation)CRGAN · MLR-CUHK03Rank-1 (%): 79.7 -> 82.1Improved
use joint representation [f,g] instead of g only (ablation)CRGAN · CAVIARRank-1 (%): 38.9 -> 42.8Improved
use f only rather than g only (ablation)CRGAN · CAVIARRank-1 (%): 38.9 -> 41.5Improved
test on unseen down-sampling rate r=8 instead of seen ratesCRGAN · MLR-CUHK03Rank-1 (%): 82.1 -> 78.6Hurt
use CRGAN instead of CSR-GAN on unseen resolutionCRGAN vs CSR-GAN · MLR-CUHK03 (unseen r=8)Rank-1 (%): 62.1 -> 78.6Improved

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