Learning Resolution-Invariant Deep Representations for Person Re-Identification
This addresses the practical issue of resolution mismatch in person re-identification for real-world surveillance applications, representing an incremental improvement by integrating adversarial learning into an end-to-end framework.
The paper tackles the problem of cross-resolution person re-identification by proposing a novel network architecture (RAIN) that extracts resolution-invariant representations, enabling recognition of low-resolution query images even at unseen resolutions and showing scalability for semi-supervised re-ID.
Person re-identification (re-ID) solves the task of matching images across cameras and is among the research topics in vision community. Since query images in real-world scenarios might suffer from resolution loss, how to solve the resolution mismatch problem during person re-ID becomes a practical problem. Instead of applying separate image super-resolution models, we propose a novel network architecture of Resolution Adaptation and re-Identification Network (RAIN) to solve cross-resolution person re-ID. Advancing the strategy of adversarial learning, we aim at extracting resolution-invariant representations for re-ID, while the proposed model is learned in an end-to-end training fashion. Our experiments confirm that the use of our model can recognize low-resolution query images, even if the resolution is not seen during training. Moreover, the extension of our model for semi-supervised re-ID further confirms the scalability of our proposed method for real-world scenarios and applications.