REVIEW 2 cited by
1st Place Solution to VisDA-2020: Bias Elimination for Domain Adaptive Pedestrian Re-identification
Not yet reviewed by Pith; the record is open.
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
read the original abstract
This paper presents our proposed methods for domain adaptive pedestrian re-identification (Re-ID) task in Visual Domain Adaptation Challenge (VisDA-2020). Considering the large gap between the source domain and target domain, we focused on solving two biases that influenced the performance on domain adaptive pedestrian Re-ID and proposed a two-stage training procedure. At the first stage, a baseline model is trained with images transferred from source domain to target domain and from single camera to multiple camera styles. Then we introduced a domain adaptation framework to train the model on source data and target data simultaneously. Different pseudo label generation strategies are adopted to continuously improve the discriminative ability of the model. Finally, with multiple models ensembled and additional post processing approaches adopted, our methods achieve 76.56% mAP and 84.25% rank-1 on the test set. Codes are available at https://github.com/vimar-gu/Bias-Eliminate-DA-ReID
Forward citations
Cited by 2 Pith papers
-
Exploring the Camera Bias of Person Re-identification
Per-camera feature normalization at test time reduces camera bias and improves cross-domain person re-identification, and two simple training modifications substantially improve unsupervised ReID.
-
DART$^3$: Leveraging Distance for Test Time Adaptation in Person Re-Identification
A test-time adaptation method for person re-identification that learns per-camera scale and shift parameters with a top-k Euclidean distance objective, reducing camera bias without source data.
Discussion (0). Continue with ORCID to comment.