Person Re Identification On Dukemtmc Reid

评估指标

Rank-1

mAP

评测结果

各个模型在此基准测试上的表现结果

			Paper Title	Repository
DenseIL	-	97.1	Dense Interaction Learning for Video-based Person Re-identification	-
CTL Model (ResNet50, 256x128)	95.6	96.1	On the Unreasonable Effectiveness of Centroids in Image Retrieval
BPBreID (RK)	93.9	92.9	Body Part-Based Representation Learning for Occluded Person Re-Identification
Unsupervised Pre-training (ResNet101+RK)	93.99	92.77	Unsupervised Pre-training for Person Re-identification
st-ReID(RE, RK,Cam)	94.5	92.7	Spatial-Temporal Person Re-identification
RGT&RGPR (RK)	94.3	92.7	Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method
Viewpoint-Aware Loss(RK)	93.9	91.8	Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification
LDS (ResNet50 + RK)	92.91	91.0	Learning to Disentangle Scenes for Person Re-identification
Adaptive L2 Regularization (with re-ranking)	92.2	90.7	Adaptive L2 Regularization in Person Re-Identification
FlipReID (with re-ranking)	93.0	90.7	FlipReID: Closing the Gap between Training and Inference in Person Re-Identification
DAAF-BoT(RK)	91.7	89.6	Deep Attention Aware Feature Learning for Person Re-Identification
Auto-ReID(RK)	91.4	89.2	Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification
RPTM	93.5	89.2	Relation Preserving Triplet Mining for Stabilising the Triplet Loss in Re-identification Systems
BoT Baseline(RK)	90.2	89.1	Bag of Tricks and A Strong Baseline for Deep Person Re-identification
st-ReID+InSTD	-	89.1	Learning Instance-level Spatial-Temporal Patterns for Person Re-identification
Top-DB-Net + RK	90.9	88.6	Top-DB-Net: Top DropBlock for Activation Enhancement in Person Re-Identification
DG-Net(RK)	90.26	88.31	Joint Discriminative and Generative Learning for Person Re-identification
PyrNet (+ReRank)	90.3	87.7	Aggregating Deep Pyramidal Representations for Person Re-Idenfitication	-
Deep Constrained Dominant Sets	88.5	86.1	Deep Constrained Dominant Sets for Person Re-identification
Parameter-Free Spatial Attention	89.0	85.9	Parameter-Free Spatial Attention Network for Person Re-Identification

0 of 94 row(s) selected.

Command Palette

Person Re Identification On Dukemtmc Reid

评估指标

评测结果