半监督目标检测(Semi-supervised Object Detection,以下简称SSOD)旨在利用大量的无标注数据来提高模型的检测能力。然而,一般的SSOD方法都假设无标注数据不包含分布外 (Out-of-distribution, OOD) 的类别,这对于大规模的无标注数据集是不现实的。因此,作者提出了一种更符合实际的研究问题——开集半监
In this paper, we consider a more practical yet challenging problem, Open-Set Semi-Supervised Object Detection (OSSOD). We first find the existing SSOD method obtains a lower performance gain in open-set conditions, and this is caused by the semantic expansion, where the distracting OOD ...
Paper tables with annotated results for Class-balanced Open-set Semi-supervised Object Detection for Medical Images
Xu, M., et al.: End-to-end semi-supervised object detection with soft teacher. arXiv preprintarXiv:2106.09018(2021) Yao, L., et al.: DetCLIPv2: scalable open-vocabulary object detection pre-training via word-region alignment (2023) ...
Behavior regularized prototypical networks for semi-supervised few-shot image classification 2021, Pattern Recognition Citation Excerpt : Few-Shot Learning (FSL) aims to learn new visual concepts with very limited examples and generalize well to their variants. To reduce the dependence on large amount...
OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers. Kuniaki Saito, Donghyun Kim, Kate Saenko. (ArXiv 2021).[code]. Zero-Shot Open Set Detection by Extending CLIP. Sepideh Esmaeilpour, Bing Liu, Eric Robertson, Lei Shu. (ArXiv 2021). ...
几篇论文实现代码:《OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers》(NeurIPS 2021) GitHub:https:// github.com/VisionLearningGroup/OP_Match [fig8] 《Learn...
OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers. arXiv 2021, arXiv:2105.14148. [Google Scholar] Heras, J.; Royo, D.; Ángel, M. A Good Closed-Set Classifier Is All You Need for the AIROGS Challenge. Available online: http://rumc-gcorg-p-public...
[38] uses level set evolution as a postprocessing step to a CNN, and trains on unlabeled data processed in a semi-supervised fashion. [21] adds the level set energy in the loss function and uses a CNN to directly predict the level set function for salient object...
At the problem level, this establishes an interesting connection between knowledge distillation with open-set semi-supervised learning (SSL). Extensive experiments show that our SRD outperforms significantly previous state-of-the-art knowledge distillation methods on both coarse object classification and ...