Hierarchical Open-Set Object Detection in Unseen Data
Open Access
Abstract
In this paper, we propose an open-set object detection framework based on a dynamic hierarchical structure with incremental learning capabilities for unseen object classes. We were motivated by the observation that deep features extracted from visual objects show a strong hierarchical clustering property. The hierarchical feature model (HFM) was used to learn a new object class by using collaborative sampling (CS), and open-set-aware active semi-supervised learning (ASSL) algorithms. We divided object proposals into superclasses by using the agglomerative clustering algorithm. Data samples in each superclass node were classified into multiple augmented class nodes instead of directly associating with regular object classes. One or more augmented class nodes are related to a regular object class, and each augmented class has only one superclass. Object proposals from inexperienced data distribution are assigned to an augmented class node. Dynamic HFM nodes in the decision path are assembled to constitute an ensemble prediction, and the new augmented object is associated with a new regular object class. Our experimental results showed that the proposed method uses standard benchmark datasets such as PASCAL VOC, MS COCO, ILSVRC DET, and local datasets to perform better than state-of-the-art techniques.Keywords
This publication has 36 references indexed in Scilit:
- A Continuous Learning Framework for Activity Recognition Using Deep Hybrid Feature ModelsIEEE Transactions on Multimedia, 2015
- Characterization and performance of the ASIC (CITIROC) front-end of the ASTRI cameraNuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Collaborative Active and Semisupervised Learning for Hyperspectral Remote Sensing Image ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2014
- Lymphocyte-style word representations2014
- Enhancing the Labelling Technique of Suffix Tree Clustering AlgorithmInternational Journal of Data Mining & Knowledge Management Process, 2014
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Toward Open Set RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009