TY - GEN
T1 - IMPROVING OPEN-SET RECOGNITION WITH BAYESIAN METRIC LEARNING
AU - Chen, Tong
AU - Feng, Guanchao
AU - Djurić, Petar M.
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Conventionally, it is often assumed that the training and testing data distributions are the same and that all classes in the test set are observed in the training set. However, this assumption may not be true in real-world tasks. In practice, there may be test samples from classes that were unknown during training. In such cases, one would like the adopted model to have the capacity to classify such samples into a “none of the above” class. This task is known as open-set recognition, and it has gained significant attention in recent years. In this paper, we propose a novel distance-based open-set recognition approach by constructing task-specific distance metrics with Gaussian processes. Our experimental results demonstrate that the proposed approach outperforms state-of-the-art methods on both synthetic and real-world datasets.
AB - Conventionally, it is often assumed that the training and testing data distributions are the same and that all classes in the test set are observed in the training set. However, this assumption may not be true in real-world tasks. In practice, there may be test samples from classes that were unknown during training. In such cases, one would like the adopted model to have the capacity to classify such samples into a “none of the above” class. This task is known as open-set recognition, and it has gained significant attention in recent years. In this paper, we propose a novel distance-based open-set recognition approach by constructing task-specific distance metrics with Gaussian processes. Our experimental results demonstrate that the proposed approach outperforms state-of-the-art methods on both synthetic and real-world datasets.
KW - distance metric learning
KW - Gaussian processes
KW - multiclass classification
KW - novelty detection
KW - open-set recognition
UR - https://www.scopus.com/pages/publications/85195425651
U2 - 10.1109/ICASSP48485.2024.10446665
DO - 10.1109/ICASSP48485.2024.10446665
M3 - Conference contribution
AN - SCOPUS:85195425651
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 6185
EP - 6189
BT - 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024
Y2 - 14 April 2024 through 19 April 2024
ER -