Adversarial Kinetic Prototype Framework for Open Set Recognition
- 10 January 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (7) , 9238-9251
Abstract
Due to the complexity of real-world applications, open set recognition is often more practical than closed set recognition. Compared with closed set recognition, open set recognition needs not only to recognize known classes but also to identify unknown classes. Different from most of the current methods, we proposed three novel frameworks with kinetic pattern to address the open set recognition problems, and they are kinetic prototype framework (KPF), adversarial KPF (AKPF), and an upgraded version of the AKPF, AKPF $++$ . First, KPF introduces a novel kinetic margin constraint radius, which can improve the compactness of the known features to increase the robustness for the unknowns. Based on KPF, AKPF can generate adversarial samples and add these samples into the training phase, which can improve the performance with the adversarial motion of the margin constraint radius. Compared with AKPF, AKPF $++$ further improves the performance by adding more generated data into the training phase. Extensive experimental results on various benchmark datasets indicate that the proposed frameworks with kinetic pattern are superior to other existing approaches and achieve the state-of-the-art performance.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (61701379, 62192714)
- stabilization support of National Radar Signal Processing Laboratory (KGJ202204)
- Fundamental Research Funds for the Central Universities (QTZX22160)
- Shanghai Aerospace Science and Technology Innovation Foundation (SAST2021-011)
This publication has 32 references indexed in Scilit:
- Self-Paced Balance Learning for Clinical Skin Disease RecognitionIEEE Transactions on Neural Networks and Learning Systems, 2019
- Open-set human activity recognition based on micro-Doppler signaturesPattern Recognition, 2019
- Open Set Learning with Counterfactual Images2018
- Robust Classification with Convolutional Prototype Learning2018
- Sparse Temporal Encoding of Visual Features for Robust Object Recognition by Spiking NeuronsIEEE Transactions on Neural Networks and Learning Systems, 2018
- Towards Open Set Deep Networks2016
- Deep Learning Face Attributes in the Wild2015
- Probability Models for Open Set RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Toward Open Set RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Fast translation invariant classification of HRR range profiles in a zero phase representationIEE Proceedings - Radar, Sonar and Navigation, 2003