TY - GEN
T1 - OSCARS
T2 - 2022 International Conference on Multimedia Retrieval, ICMR 2022
AU - Guo, Xiaoyuan
AU - Duan, Jiali
AU - Purkayastha, Saptarshi
AU - Trivedi, Hari
AU - Gichoya, Judy Wawira
AU - Banerjee, Imon
N1 - Publisher Copyright:
© 2022 ACM.
PY - 2022/6/27
Y1 - 2022/6/27
N2 - Improving the retrieval relevance on noisy datasets is an emerging need for the curation of a large-scale clean dataset in the medical domain. While existing methods can be applied for class-wise retrieval (aka. inter-class), they cannot distinguish the granularity of likeness within the same class (aka. intra-class). The problem is exacerbated on medical external datasets, where noisy samples of the same class are treated equally during training. Our goal is to identify both intra/inter-class similarities for fine-grained retrieval. To achieve this, we propose an Outlier-Sensitive Content-based rAdiologhy Retrieval System (OSCARS), consisting of two steps. First, we train an outlier detector on a clean internal dataset in an unsupervised manner. Then we use the trained detector to generate the anomaly scores on the external dataset, whose distribution will be used to bin intra-class variations. Second, we propose a quadruplet (a, p, nintra, ninter) sampling strategy, where intra-class negatives nintra are sampled from bins of the same class other than the bin anchor a belongs to, while n_inter are randomly sampled from inter-classes. We suggest a weighted metric learning objective to balance the intra and inter-class feature learning. We experimented on two representative public radiography datasets. Experiments show the effectiveness of our approach. The training and evaluation code can be found in https://github.com/XiaoyuanGuo/oscars.
AB - Improving the retrieval relevance on noisy datasets is an emerging need for the curation of a large-scale clean dataset in the medical domain. While existing methods can be applied for class-wise retrieval (aka. inter-class), they cannot distinguish the granularity of likeness within the same class (aka. intra-class). The problem is exacerbated on medical external datasets, where noisy samples of the same class are treated equally during training. Our goal is to identify both intra/inter-class similarities for fine-grained retrieval. To achieve this, we propose an Outlier-Sensitive Content-based rAdiologhy Retrieval System (OSCARS), consisting of two steps. First, we train an outlier detector on a clean internal dataset in an unsupervised manner. Then we use the trained detector to generate the anomaly scores on the external dataset, whose distribution will be used to bin intra-class variations. Second, we propose a quadruplet (a, p, nintra, ninter) sampling strategy, where intra-class negatives nintra are sampled from bins of the same class other than the bin anchor a belongs to, while n_inter are randomly sampled from inter-classes. We suggest a weighted metric learning objective to balance the intra and inter-class feature learning. We experimented on two representative public radiography datasets. Experiments show the effectiveness of our approach. The training and evaluation code can be found in https://github.com/XiaoyuanGuo/oscars.
KW - deep metric learning
KW - medical image retrieval
KW - outlier detection
UR - http://www.scopus.com/inward/record.url?scp=85134073836&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85134073836&partnerID=8YFLogxK
U2 - 10.1145/3512527.3531425
DO - 10.1145/3512527.3531425
M3 - Conference contribution
AN - SCOPUS:85134073836
T3 - ICMR 2022 - Proceedings of the 2022 International Conference on Multimedia Retrieval
SP - 11
EP - 18
BT - ICMR 2022 - Proceedings of the 2022 International Conference on Multimedia Retrieval
PB - Association for Computing Machinery, Inc
Y2 - 27 June 2022 through 30 June 2022
ER -