Resolution-invariant Person Re-Identification
It addresses resolution variance in person re-identification for real-world surveillance applications, representing an incremental advance with specific performance gains.
This paper tackles the problem of person re-identification across varying image resolutions by jointly training a foreground-focus super-resolution module and a resolution-invariant feature extractor, achieving Rank-1 accuracy improvements of 2.9% on CAVIAR and 2.6% on MLR-CUHK03 compared to state-of-the-art methods.
Exploiting resolution invariant representation is critical for person Re-Identification (ReID) in real applications, where the resolutions of captured person images may vary dramatically. This paper learns person representations robust to resolution variance through jointly training a Foreground-Focus Super-Resolution (FFSR) module and a Resolution-Invariant Feature Extractor (RIFE) by end-to-end CNN learning. FFSR upscales the person foreground using a fully convolutional auto-encoder with skip connections learned with a foreground focus training loss. RIFE adopts two feature extraction streams weighted by a dual-attention block to learn features for low and high resolution images, respectively. These two complementary modules are jointly trained, leading to a strong resolution invariant representation. We evaluate our methods on five datasets containing person images at a large range of resolutions, where our methods show substantial superiority to existing solutions. For instance, we achieve Rank-1 accuracy of 36.4% and 73.3% on CAVIAR and MLR-CUHK03, outperforming the state-of-the art by 2.9% and 2.6%, respectively.