Interpolation-based Semi-supervised Learning for Object Detection

Jisoo Jeong, Vikas Verma, Minsung Hyun, Juho Kannala, Nojun Kwak

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

38 Sitaatiot (Scopus)


Despite the data labeling cost for the object detection tasks being substantially more than that of the classification tasks, semi-supervised learning methods for object detection have not been studied much. In this paper, we propose an Interpolation-based Semi-supervised learning method for object Detection (ISD), which considers and solves the problems caused by applying conventional Interpolation Regularization (IR) directly to object detection. We divide the output of the model into two types according to the objectness scores of both original patches that are mixed in IR. Then, we apply a separate loss suitable for each type in an unsupervised manner. The proposed losses dramatically improve the performance of semi-supervised learning as well as supervised learning. In the supervised learning setting, our method improves the baseline methods by a significant margin. In the semi-supervised learning setting, our algorithm improves the performance on a benchmark dataset (PASCAL VOC and MSCOCO) in a benchmark architecture (SSD). Our code is available at
OtsikkoProceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
ISBN (elektroninen)978-1-6654-4509-2
ISBN (painettu)978-1-6654-4510-8
DOI - pysyväislinkit
TilaJulkaistu - 13 marrask. 2021
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIEEE Conference on Computer Vision and Pattern Recognition - Virtual, online, Nashville, Yhdysvallat
Kesto: 19 kesäk. 202125 kesäk. 2021


NimiIEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (elektroninen)2575-7075


ConferenceIEEE Conference on Computer Vision and Pattern Recognition


Sukella tutkimusaiheisiin 'Interpolation-based Semi-supervised Learning for Object Detection'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä