Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting
arXiv:2107.03576
Abstract
Pedestrian attribute recognition aims to assign multiple attributes to one pedestrian image captured by a video surveillance camera. Although numerous methods are proposed and make tremendous progress, we argue that it is time to step back and analyze the status quo of the area. We review and rethink the recent progress from three perspectives. First, given that there is no explicit and complete definition of pedestrian attribute recognition, we formally define and distinguish pedestrian attribute recognition from other similar tasks. Second, based on the proposed definition, we expose the limitations of the existing datasets, which violate the academic norm and are inconsistent with the essential requirement of practical industry application. Thus, we propose two datasets, PETA\textsubscript{} and RAP\textsubscript{}, constructed following the zero-shot settings on pedestrian identity. In addition, we also introduce several realistic criteria for future pedestrian attribute dataset construction. Finally, we reimplement existing state-of-the-art methods and introduce a strong baseline method to give reliable evaluations and fair comparisons. Experiments are conducted on four existing datasets and two proposed datasets to measure progress on pedestrian attribute recognition.
arXiv comment13 pages, 6 figures, journal version of arXiv:2005.11909, submitted to TIP. Code is available https://github.com/valencebond/Rethinking_of_PAR
References in corpus (4)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild
- Improving Person Re-identification by Attribute and Identity Learning
- A Richly Annotated Dataset for Pedestrian Attribute Recognition