Journal
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Volume 44, Issue 6, Pages 3349-3363Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2020.3046647
Keywords
Cognition; Proposals; Object detection; Supervised learning; Semantics; Task analysis; Network architecture; Weakly supervised object detection; multiple-instance learning; graphical convolutional network
Funding
- Key R&D Program of Guangdong Province [2019B010110001]
- National Science Foundation of China [61876140, U1801265]
- Research Funds for Interdisciplinary subject, NWPU
Ask authors/readers for more resources
Weakly supervised object detection has received great attention in recent years in the computer vision community. However, existing approaches mostly focus on visual appearance and ignore the use of context information. This paper proposes a weakly supervised learning framework that incorporates proposal-level and semantic-level context, leading to improved learning performance through deep multiple instance reasoning. Experimental results demonstrate the superior performance of the proposed approach on widely used benchmarks.
In recent years, weakly supervised object detection has attracted great attention in the computer vision community. Although numerous deep learning-based approaches have been proposed in the past few years, such an ill-posed problem is still challenging and the learning performance is still behind the expectation. In fact, most of the existing approaches only consider the visual appearance of each proposal region but ignore to make use of the helpful context information. To this end, this paper introduces two levels of context into the weakly supervised learning framework. The first one is the proposal-level context, i.e., the relationship of the spatially adjacent proposals. The second one is the semantic-level context, i.e., the relationship of the co-occurring object categories. Therefore, the proposed weakly supervised learning framework contains not only the cognition process on the visual appearance but also the reasoning process on the proposal- and semantic-level relationships, which leads to the novel deep multiple instance reasoning framework. Specifically, built upon a conventional CNN-based network architecture, the proposed framework is equipped with two additional graph convolutional network-based reasoning models to implement object location reasoning and multi-label reasoning within an end-to-end network training procedure. Comprehensive experiments on the widely used PASCAL VOC and MS COCO benchmarks have been implemented, which demonstrate the superior capacity of the proposed approach when compared with other state-of-the-art methods and baseline models.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available