Pith. sign in

REVIEW 5 cited by

Deep Transfer Learning for Person Re-identification

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1611.05244 v2 pith:I76GIWYX submitted 2016-11-16 cs.CV

Mengyue Geng , Yaowei Wang , Tao Xiang , Yonghong Tian This is my paper · ORCID
classification cs.CV
keywords deepmodelslearningre-idtransfermodelclassificationdatasets
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Person re-identification (Re-ID) poses a unique challenge to deep learning: how to learn a deep model with millions of parameters on a small training set of few or no labels. In this paper, a number of deep transfer learning models are proposed to address the data sparsity problem. First, a deep network architecture is designed which differs from existing deep Re-ID models in that (a) it is more suitable for transferring representations learned from large image classification datasets, and (b) classification loss and verification loss are combined, each of which adopts a different dropout strategy. Second, a two-stepped fine-tuning strategy is developed to transfer knowledge from auxiliary datasets. Third, given an unlabelled Re-ID dataset, a novel unsupervised deep transfer learning model is developed based on co-training. The proposed models outperform the state-of-the-art deep Re-ID models by large margins: we achieve Rank-1 accuracy of 85.4\%, 83.7\% and 56.3\% on CUHK03, Market1501, and VIPeR respectively, whilst on VIPeR, our unsupervised model (45.1\%) beats most supervised models.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Progressive Transfer Learning

    cs.CV 2019-08 conditional novelty 6.0 of 10

    A new convolutional memory cell that aggregates dataset information across mini-batches improves fine-tuning accuracy for person re-identification and image classification.

  2. ABD-Net: Attentive but Diverse Person Re-Identification

    cs.CV 2019-08 conditional novelty 6.0 of 10

    ABD-Net combines channel and position attention with a spectral orthogonality penalty on features and weights, and reports state-of-the-art mAP on Market-1501, DukeMTMC-Re-ID, and MSMT17.

  3. Segmentation Mask Guided End-to-End Person Search

    cs.CV 2019-08 conditional novelty 5.0 of 10

    Jointly training detection, re-identification and segmentation with partially labeled masks improves person search on CUHK-SYSU to 86.3% mAP and 86.5% top-1 accuracy.

  4. Second-order Non-local Attention Networks for Person Re-identification

    cs.CV 2019-08 conditional novelty 4.0 of 10

    A second-order non-local attention module, trained with a generalized DropBlock, achieves state-of-the-art person re-identification on CUHK03 and competitive results on Market1501 and DukeMTMC-reID.

  5. Learning Deep Representations by Mutual Information for Person Re-identification

    cs.CV 2019-08 reject novelty 4.0 of 10

    Adding a Deep InfoMax-style adversarial loss to IDE and PCB person re-identification baselines gives modest rank-1/mAP gains, but the claimed mutual information between input image and encoder output is not implemente...

Pith tools