mlsanityData to 7 Oct 2026

Stronger Baseline for Person Re-Identification

arXiv 2112.01059 ↗First posted 2 Dec 2021cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Person re-identification (re-ID) aims to identify the same person of interest across non-overlapping capturing cameras, which plays an important role in visual surveillance applications and computer vision research areas. Fitting a robust appearance-based representation extractor with limited collected training data is crucial for person re-ID due to the high expanse of annotating the identity of unlabeled data. In this work, we propose a Stronger Baseline for person re-ID, an enhancement version of the current prevailing method, namely, Strong Baseline, with tiny modifications but a faster convergence rate and higher recognition performance. With the aid of Stronger Baseline, we obtained the third place (i.e., 0.94 in mAP) in 2021 VIPriors Re-identification Challenge without the auxiliary of ImageNet-based pre-trained parameter initialization and any extra supplemental dataset.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 29 references that are in the map. First posted on arXiv 2 Dec 2021.

Builds on

20 of 29 references.

References · 20

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  3. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  4. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 784
  5. 2018AutoAugment: Learning Augmentation Policies from Datacited by 728
  6. 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 472
  7. 2019Bag of Tricks and A Strong Baseline for Deep Person Re-identificationcited by 429
  8. 2018Harmonious Attention Network for Person Re-Identificationcited by 211
  9. 2017Beyond triplet loss: a deep quadruplet network for person re-identificationcited by 172
  10. 2016Person Re-identification in the Wildcited by 157
  11. 2018Multi-Level Factorisation Net for Person Re-Identificationcited by 58
  12. 2018STA: Spatial-Temporal Attention for Large-Scale Video-based Person Re-Identificationcited by 46
8 more
  1. 2017SVDNet for Pedestrian Retrievalcited by 43
  2. 2016End-to-End Comparative Attention Networks for Person Re-identificationcited by 42
  3. 2016Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identificationcited by 41
  4. 2018SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identificationcited by 27
  5. 2019Spatially and Temporally Efficient Non-local Attention Network for Video-based Person Re-Identificationcited by 23
  6. 2018SCAN: Self-and-Collaborative Attention Network for Video Person Re-identificationcited by 12
  7. 2018Efficient and Deep Person Re-Identification using Multi-Level Similaritycited by 7
  8. 2019HorNet: A Hierarchical Offshoot Recurrent Network for Improving Person Re-ID via Image Captioningcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024AG-ReID.v2: Bridging Aerial and Ground Views for Person Re-identificationcited by 19