Mixed Supervised Object Detection with Robust Objectness Transfer

Yan Li, Junge Zhang, Jianguo Zhang, Kaiqi Huang

Research output: Contribution to journalArticle

185 Downloads (Pure)

Abstract

In this paper, we consider the problem of leveraging existing fully labeled categories to improve the weakly supervised detection (WSD) of new object categories, which we refer to as mixed supervised detection (MSD). Different from previous MSD methods that directly transfer the pre-trained object detectors from existing categories to new categories, we propose a more reasonable and robust objectness transfer approach for MSD. In our framework, we first learn domain-invariant objectness knowledge from the existing fully labeled categories. The knowledge is modeled based on invariant features that are robust to the distribution discrepancy between the existing categories and new categories; therefore the resulting knowledge would generalize well to new categories and could assist detection models to reject distractors (e.g., object parts) in weakly labeled images of new categories. Under the guidance of learned objectness knowledge, we utilize multiple instance learning (MIL) to model the concepts of both objects and distractors and to further improve the ability of rejecting distractors in weakly labeled images. Our robust objectness transfer approach outperforms the existing MSD methods, and achieves state-of-the-art results on the challenging ILSVRC2013 detection dataset and the PASCAL VOC datasets.
Original languageEnglish
Number of pages14
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
DOIs
Publication statusPublished - 28 Feb 2018

Keywords

  • Cats
  • Detectors
  • Face
  • Mixed supervised detection
  • Object detection
  • Robust objectness transfer
  • Robustness
  • Semantics
  • Training
  • Weakly supervised detection

Fingerprint Dive into the research topics of 'Mixed Supervised Object Detection with Robust Objectness Transfer'. Together they form a unique fingerprint.

  • Profiles

    No photo of Jianguo Zhang

    Zhang, Jianguo

    Person: Associate Staff

    Cite this