Exploiting Web Images for Weakly Supervised Object Detection
- 11 October 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 21 (5) , 1135-1146
Abstract
In recent years, the performance of object detection has advanced significantly with the evolution of deep convolutional neural networks. However, the state-of-the-art object detection methods still rely on accurate bounding box annotations that require extensive human labelling. Object detection without bounding box annotations, i.e, weakly supervised detection methods, are still lagging far behind. As weakly supervised detection only uses image level labels and does not require the ground truth of bounding box location and label of each object in an image, it is generally very difficult to distill knowledge of the actual appearances of objects. Inspired by curriculum learning, this paper proposes an easy-to-hard knowledge transfer scheme that incorporates easy web images to provide prior knowledge of object appearance as a good starting point. While exploiting large-scale free web imagery, we introduce a sophisticated labour free method to construct a web dataset with good diversity in object appearance. After that, semantic relevance and distribution relevance are introduced and utilized in the proposed curriculum training scheme. Our end-to-end learning with the constructed web data achieves remarkable improvement across most object classes, especially for the classes that are often considered hard in other works.Keywords
All Related Versions
Funding Information
- MoE Tier-2 (2016-T2-2-065)
- Tier-1 (2018-T1-001-115)
- NTU CoE (2016)
This publication has 27 references indexed in Scilit:
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Visual Recognition by Learning From Web Data via Weakly Supervised Domain GeneralizationIEEE Transactions on Neural Networks and Learning Systems, 2016
- Weakly Supervised Object Localization with Multi-Fold Multiple Instance LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Relaxing from Vocabulary: Robust Weakly-Supervised Deep Learning for Vocabulary-Free Image Tagging2015
- Webly Supervised Learning of Convolutional Networks2015
- Augmenting Strong Supervision Using Web Data for Fine-Grained Categorization2015
- Weakly supervised object detection with convex clustering2015
- Learning Everything about Anything: Webly-Supervised Visual Concept Learning2014
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories2006
- Solving the multiple instance problem with axis-parallel rectanglesArtificial Intelligence, 1997