Progressive Pseudo Labeling for Multi-dataset Detection over Unified Label Space

Kai Ye, Zepeng Huang, Yilei Xiong, Yu Gao, Jinheng Xie, Linlin Shen

Research output: Journal PublicationArticlepeer-review

Abstract

Existing multi-dataset detection works mainly focus on the performance of detector on each of the datasets, with different label spaces. However, in real-world applications, a unified label space across multiple datasets is usually required. To address such a gap, we propose a progressive pseudo labeling (PPL) approach to detect objects across different datasets, over a unified label space. Specifically, we employ the widely used architecture of teacher-student model pair to jointly refine pseudo labels and train the unified object detector. The student model learns from both annotated labels and pseudo labels from the teacher model, which is updated by the exponential moving average (EMA) of the student. Three modules, i.e. Entropyguided Adaptive Threshold (EAT), Global Classification Module (GCM) and Scene-Aware Fusion (SAF) strategy, are proposed to handle the noise of pseudo labels and fit the overall distribution. Extensive experiments are conducted on different multi-dataset benchmarks. The results demonstrate that our proposed method significantly outperforms the state-of-the-art and is even comparable with supervised methods trained using annotations of all labels.

Original languageEnglish
JournalIEEE Transactions on Multimedia
DOIs
Publication statusAccepted/In press - 2024

Keywords

  • Multi-dataset
  • Object detection
  • Pseudo Label
  • Unified Label Space

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Progressive Pseudo Labeling for Multi-dataset Detection over Unified Label Space'. Together they form a unique fingerprint.

Cite this