AI Paper Atlas

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

TransReID: Transformer-Based Object Re-Identification

Shuting He, Hao Luo, Pichao Wang, Fan Wang, Hao Li, Wei Jiang

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Cross-modality and occlusion re-identification · 1,396 citations (OpenAlex)

This paper tried a common change: Add label smoothing

add label smoothing · MSMT17 · mAP: 61.0 -> 59.8 Hurt

What 190 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 jigsaw patch module (4 groups) (ablation)ViT-B/16 baseline · MSMT17mAP: 61.0 -> 63.6Improved
add jigsaw patch module (4 groups) (ablation)ViT-B/16 baseline · VeRi-776mAP: 78.2 -> 79.2Improved
add shift and shuffle rearrangement inside JPM (ablation)JPM · MSMT17mAP: 63.1 -> 63.6Improved
add shift and shuffle rearrangement inside JPM (ablation)JPM · VeRi-776mAP: 79.0 -> 79.2Improved
increase JPM groups from 1 to 4 (ablation)JPM · MSMT17mAP: 62.9 -> 63.6Improved
add camera side information embedding (ablation)ViT-B/16 baseline · MSMT17mAP: 61.0 -> 62.4Improved
encode camera and viewpoint jointly instead of summing embeddings (ablation)SIE · VeRi-776mAP: 78.3 -> 79.6Improved
use overlapping patches with step size 12 (ablation)ViT-B/16 baseline · MSMT17mAP: 61.0 -> 64.4Improved
combine JPM and SIE (ablation)ViT-B/16 baseline · MSMT17mAP: 61.0 -> 64.9Improved
tune SIE weight lambda to 2.0 (ablation)SIE · MSMT17mAP: 61.0 -> 63.0Improved
add position embeddings (ablation)ViT-B/16 baseline · MSMT17mAP: 22.4 -> 61.0Improved
use Adam instead of SGD (ablation)ViT-B/16 baseline · MSMT17mAP: 61.0 -> 37.4Hurt

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