English

PGTRNet: Two-phase Weakly Supervised Object Detection with Pseudo Ground Truth Refinement

Computer Vision and Pattern Recognition 2022-03-21 v2

Abstract

Current state-of-the-art weakly supervised object detection (WSOD) studies mainly follow a two-stage training strategy which integrates a fully supervised detector (FSD) with a pure WSOD model. There are two main problems hindering the performance of the two-phase WSOD approaches, i.e., insufficient learning problem and strict reliance between the FSD and the pseudo ground truth (PGT) generated by the WSOD model. This paper proposes pseudo ground truth refinement network (PGTRNet), a simple yet effective method without introducing any extra learnable parameters, to cope with these problems. PGTRNet utilizes multiple bounding boxes to establish the PGT, mitigating the insufficient learning problem. Besides, we propose a novel online PGT refinement approach to steadily improve the quality of PGT by fully taking advantage of the power of FSD during the second-phase training, decoupling the first and second-phase models. Elaborate experiments are conducted on the PASCAL VOC 2007 benchmark to verify the effectiveness of our methods. Experimental results demonstrate that PGTRNet boosts the backbone model by 2.1% mAP and achieves the state-of-the-art performance.

Keywords

Cite

@article{arxiv.2108.11439,
  title  = {PGTRNet: Two-phase Weakly Supervised Object Detection with Pseudo Ground Truth Refinement},
  author = {Jun Wang and Hefeng Zhou and Xiaohan Yu},
  journal= {arXiv preprint arXiv:2108.11439},
  year   = {2022}
}

Comments

This paper was accepted by ICASSP2022. arXiv admin note: substantial text overlap with arXiv:2104.00231

R2 v1 2026-06-24T05:25:19.035Z