Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting
Preprint
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{$ZS$} 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.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Improve Person Re-Identification With Part Awareness LearningIEEE Transactions on Image Processing, 2020
- A Strong Baseline and Batch Normalization Neck for Deep Person Re-IdentificationIEEE Transactions on Multimedia, 2019
- GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the WildIEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
- Improving person re-identification by attribute and identity learningPattern Recognition, 2019
- Attention-Based Pedestrian Attribute AnalysisIEEE Transactions on Image Processing, 2019
- Recurrent Prediction with Spatio-temporal Attention for Crowd Attribute RecognitionIEEE Transactions on Circuits and Systems for Video Technology, 2019
- A Richly Annotated Pedestrian Dataset for Person Retrieval in Real Surveillance ScenariosIEEE Transactions on Image Processing, 2018
- Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the UglyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009