Unsupervised object detection with scene-adaptive concept learning
- 28 May 2021
- journal article
- research article
- Published by Zhejiang University Press in Frontiers of Information Technology & Electronic Engineering
- Vol. 22 (5), 638-651
- https://doi.org/10.1631/fitee.2000567
Abstract
Object detection is one of the hottest research directions in computer vision, has already made impressive progress in academia, and has many valuable applications in the industry. However, the mainstream detection methods still have two shortcomings: (1) even a model that is well trained using large amounts of data still cannot generally be used across different kinds of scenes; (2) once a model is deployed, it cannot autonomously evolve along with the accumulated unlabeled scene data. To address these problems, and inspired by visual knowledge theory, we propose a novel scene-adaptive evolution unsupervised video object detection algorithm that can decrease the impact of scene changes through the concept of object groups. We first extract a large number of object proposals from unlabeled data through a pre-trained detection model. Second, we build the visual knowledge dictionary of object concepts by clustering the proposals, in which each cluster center represents an object prototype. Third, we look into the relations between different clusters and the object information of different groups, and propose a graph-based group information propagation strategy to determine the category of an object concept, which can effectively distinguish positive and negative proposals. With these pseudo labels, we can easily fine-tune the pre-trained model. The effectiveness of the proposed method is verified by performing different experiments, and the significant improvements are achieved.Keywords
This publication has 45 references indexed in Scilit:
- Person re-identification by unsupervised video matchingPattern Recognition, 2017
- SSD: Single Shot MultiBox DetectorPublished by Springer Science and Business Media LLC ,2016
- Unsupervised Visual Representation Learning by Graph-Based Consistent ConstraintsPublished by Springer Science and Business Media LLC ,2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Object Detection from Video Tubelets with Convolutional Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- The Cityscapes Dataset for Semantic Urban Scene UnderstandingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- You Only Look Once: Unified, Real-Time Object DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Fast R-CNNPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Unsupervised Object Discovery and Tracking in Video CollectionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014