Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting
This work addresses evaluation inconsistencies in pedestrian attribute recognition for surveillance applications, though it is incremental as it focuses on dataset refinement rather than a new method.
The authors tackled the problem of unreliable evaluation in pedestrian attribute recognition by exposing dataset limitations and proposing two new datasets (PETA_ZS and RAP_ZS) under zero-shot settings, leading to more reliable assessments of state-of-the-art methods.
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{$ZS$} and RAP\textsubscript{$ZS$}, 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.