26 papers with code • 8 benchmarks • 3 datasets
The main idea of instance contrastive learning is to match a same instance in different augmented views.
We demonstrate that the inconsistency problem for cluster feature representation can be solved by the cluster-level memory dictionary. By straightforwardly applying Cluster Contrast to a standard unsupervised re-ID pipeline, it achieves considerable improvements of 9. 5%, 7. 5%, 6. 6% compared to state-of-the-art purely unsupervised re-ID methods and 5. 1%, 4. 0%, 6. 5% mAP compared to the state-of-the-art unsupervised domain adaptation re-ID methods on the Market, Duke, andMSMT17 datasets. Our source code is available at https://github. com/alibaba/cluster-contrast.
The second stage considers the classification scores of each sample on different cameras as a new feature vector.
This paper considers the problem of unsupervised person re-identification (re-ID), which aims to learn discriminative models with unlabeled data.
These camera-aware proxies enable us to deal with large intra-ID variance and generate more reliable pseudo labels for learning.
The objective of unsupervised person re-identification (Re-ID) is to learn discriminative features without labor-intensive identity annotations.
Extensive experiments on three large-scale datasets, i. e., Market-1501, DukeMTMC-reID, and MSMT17, show that our coupling optimization outperforms state-of-the-art methods by a large margin.