Resource Aware Person Re-identification across Multiple Resolutions
This work addresses the problem of resource-efficient person re-identification for computer vision applications, offering incremental improvements over existing methods.
The paper tackles the problem of person re-identification by addressing the inefficiency of one-size-fits-all methods, proposing a model that uses multi-layer embeddings to improve accuracy and adapt to resource constraints. It achieves substantial improvements over previous state-of-the-art results on five datasets and demonstrates effective trade-offs between accuracy and computation.
Not all people are equally easy to identify: color statistics might be enough for some cases while others might require careful reasoning about high- and low-level details. However, prevailing person re-identification(re-ID) methods use one-size-fits-all high-level embeddings from deep convolutional networks for all cases. This might limit their accuracy on difficult examples or makes them needlessly expensive for the easy ones. To remedy this, we present a new person re-ID model that combines effective embeddings built on multiple convolutional network layers, trained with deep-supervision. On traditional re-ID benchmarks, our method improves substantially over the previous state-of-the-art results on all five datasets that we evaluate on. We then propose two new formulations of the person re-ID problem under resource-constraints, and show how our model can be used to effectively trade off accuracy and computation in the presence of resource constraints. Code and pre-trained models are available at https://github.com/mileyan/DARENet.