MIML-GAN: A GAN-Based Algorithm for Multi-Instance Multi-Label Learning on Overlapping Signal Waveform Recognition

• Published in: IEEE transactions on signal processing Vol. 71; pp. 859 - 872
• Main Authors: Pan, Zesi, Wang, Bo, Zhang, Ruibin, Wang, Shafei, Li, Yunjie, Li, Yan
• Format: Journal Article
• Language: English
• Published: New York IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Automatic waveform recognition; Feature extraction; generative adversarial network; Generative adversarial networks; Generators; Machine learning; multi-instance multi-label learning; overlapping radar signals; Recognition; residual attention learning; Semi-supervised learning; Signal processing algorithms; Supervised learning; Task analysis; Training; Waveforms
• ISSN: 1053-587X; 1941-0476
• DOI: 10.1109/TSP.2023.3242091

Existing studies for automatic waveform recognition of overlapping signals have mostly been conducted in a supervised manner. Although demonstrating superior performance in recent years, supervised methods rely heavily on sufficient labeled samples, but the acquisition of annotated data is expensive, time-consuming, and sometimes infeasible. This shortage drives the need for semi-supervised learning methods, where the unlabeled samples can be fully exploited in the training stage. In addition, multi-instance multi-label (MIML) learning is essentially another weakly supervised learning protocol, and precisely fits the form of the time-frequency images TFIs obtained from the transformation of overlapping signals. In this paper, delving into the MIML learning problem, we leverage the advantage of adversarial training to formulate an effective algorithm MIML-GAN, which is tailored to the MIML problem of overlapping signal waveform recognition. After feeding the TFIs into the network, MIML-GAN approximates the distribution of the training data using the adversarial learning principle. Subsequently, the bag-level prediction can be derived from the instance-level prediction upon the MIML discriminator through adaptive threshold calibration. Specifically, we elaborately studied the global optimality of the MIML-GAN objective function, and extensive simulations are carried out with overlapping signal dataset, validating the ascendancy of the proposed method. Comparative experiments demonstrate that the proposed algorithm possesses promising feature representation capability, and outperforms the existing semi-supervised and supervised signal waveform recognition approaches.