Orientation Driven Bag of Appearances for Person Re-identification

Ma, Liqian; Liu, Hong; Hu, Liang; Wang, Can; Sun, Qianru

doi:10.48550/arxiv.1605.02464

Cited by 2 publications

(2 citation statements)

References 45 publications

(98 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A. Experimental Setting 1) Dataset: We combine the following five ReID datasets to simulate the real-world scenarios of distributed person ReID, namely, Market-1501 [38], PKU-ReID [39], PersonX [40], Prid2011 [41], and DukeMTMC-reID [42]. We shuffle the images of these datasets into 5 distributed edge clients with non-overlapped camera-IDs.…”

Section: Training Methodologymentioning

confidence: 99%

Spatial-Temporal Federated Learning for Lifelong Person Re-identification on Distributed Edges

Zhang¹,

Gao²,

Zhang³

2022

Preprint

View full text Add to dashboard Cite

Data drift is a thorny challenge when deploying person re-identification (ReID) models into real-world devices, where the data distribution is significantly different from that of the training environment and keeps changing. To tackle this issue, we propose a federated spatial-temporal incremental learning approach, named FedSTIL, which leverages both lifelong learning and federated learning to continuously optimize models deployed on many distributed edge clients. Unlike previous efforts, FedSTIL aims to mine spatial-temporal correlations among the knowledge learnt from different edge clients. Specifically, the edge clients first periodically extract general representations of drifted data to optimize their local models. Then, the learnt knowledge from edge clients will be aggregated by centralized parameter server, where the knowledge will be selectively and attentively distilled from spatial-and temporal-dimension with carefully designed mechanisms. Finally, the distilled informative spatial-temporal knowledge will be sent back to correlated edge clients to further improve the recognition accuracy of each edge client with a lifelong learning method. Extensive experiments on a mixture of five real-world datasets demonstrate that our method outperforms others by nearly 4% in Rank-1 accuracy, while reducing communication cost by 62%. All implementation codes are publicly available on https://github.com/MSNLAB/Federated-Lifelong-Person-ReID.

show abstract

Section: Training Methodologymentioning

confidence: 99%

Spatial-Temporal Federated Learning for Lifelong Person Re-identification on Distributed Edges

Zhang¹,

Gao²,

Zhang³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Person re-ID. We create the source pool for person re-ID using 10 public datasets, including Market [57], Duke [58], MSMT17 [48] (denoted as MSMT), CUHK03 [21], RAiD [6], PersonX [40], UnrealPerson [55], RandPerson [46], PKU-Reid [31] and VIPeR [4]. Those datasets cover both synthetic and real-world data.…”

Section: Source and Target Datasetsmentioning

confidence: 99%

Large-scale Training Data Search for Object Re-identification

Yao¹,

Lei²,

Gedeon³

et al. 2023

Preprint

View full text Add to dashboard Cite

We consider a scenario where we have access to the target domain, but cannot afford on-the-fly training data annotation, and instead would like to construct an alternative training set from a large-scale data pool such that a competitive model can be obtained. We propose a search and pruning (SnP) solution to this training data search problem, tailored to object re-identification (re-ID), an application aiming to match the same object captured by different cameras. Specifically, the search stage identifies and merges clusters of source identities which exhibit similar distributions with the target domain. The second stage, subject to a budget, then selects identities and their images from the Stage I output, to control the size of the resulting training set for efficient training. The two steps provide us with training sets 80% smaller than the source pool while achieving a similar or even higher re-ID accuracy. These training sets are also shown to be superior to a few existing search methods such as random sampling and greedy sampling under the same budget on training data size. If we release the budget, training sets resulting from the first stage alone allow even higher re-ID accuracy. We provide interesting discussions on the specificity of our method to the re-ID problem and particularly its role in bridging the re-ID domain gap. The code is available at https://github.com/yorkeyao/SnP

show abstract

Orientation Driven Bag of Appearances for Person Re-identification

Cited by 2 publications

References 45 publications

Spatial-Temporal Federated Learning for Lifelong Person Re-identification on Distributed Edges

Spatial-Temporal Federated Learning for Lifelong Person Re-identification on Distributed Edges

Large-scale Training Data Search for Object Re-identification

Contact Info

Product

Resources

About