The acquisition of large-scale, precisely labeled datasets for person
re-identification (ReID) poses a significant challenge. Weakly supervised ReID
has begun to address this issue, although its performance lags behind fully
supervised methods. In response, we introduce Contrastive Multiple Instance
Learning (CMIL), a novel framework tailored for more effective weakly
supervised ReID. CMIL distinguishes itself by requiring only a single model and
no pseudo labels while leveraging contrastive losses -- a technique that has
significantly enhanced traditional ReID performance yet is absent in all prior
MIL-based approaches. Through extensive experiments and analysis across three
datasets, CMIL not only matches state-of-the-art performance on the large-scale
SYSU-30k dataset with fewer assumptions but also consistently outperforms all
baselines on the WL-market1501 and Weakly Labeled MUddy racer re-iDentification
dataset (WL-MUDD) datasets. We introduce and release the WL-MUDD dataset, an
extension of the MUDD dataset featuring naturally occurring weak labels from
the real-world application at PerformancePhoto.co. All our code and data are
accessible at
this https URL

Contrastive Multiple Instance Learning (CMIL) is a novel framework for weakly supervised person re-identification that leverages contrastive losses to enhance performance, achieving state-of-the-art results on large-scale datasets without pseudo labels and surpassing baselines on multiple datasets.