Nicu Sebe, Zhun Zhong, Fengxiang Yang, Zhiming Luo, Shaozi Li, Yaojin Lin, Yuanzheng Cai
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
This paper considers the problem of unsupervised person re-identification (re-ID), which aims to learn discriminative models with unlabeled data. One popular method is to obtain pseudo-label by clustering and use them to optimize the model. Although this kind of approach has shown promising accuracy, it is hampered by 1) noisy labels produced by clustering and 2) feature variations caused by camera shift. With the interacted gradient from meta-train and meta-test, the model is enforced to learn camera-invariant features. Extensive experiments on three re-ID benchmarks show the effectiveness and the complementary of the proposed DSCE and MetaCam. Our method outperforms the state-of-the-art methods on both fully unsupervised re-ID and unsupervised domain adaptive re-ID.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2103.04618")
get_code_for_paper("2103.04618")
have("2103.04618")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2103.04618.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2103.04618)
Connect an agent — have() is free.