期刊
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
卷 -, 期 -, 页码 9457-9465出版社
IEEE COMPUTER SOC
DOI: 10.1109/CVPR46437.2021.00934
关键词
-
资金
- EU H2020 SPRING [871245]
- AI4Media [951911]
- Caritro Deep Learning Lab of the ProM Facility of Rovereto
- [TALENT:2018YFE0118400]
In this paper, the problem of discovering new classes in unlabeled visual data given labeled data from disjoint classes is addressed. By mixing labeled examples with unlabeled examples and producing more credible pseudo-labels, the proposed OpenMix method prevents overfitting on unlabeled samples. Additionally, using high class-probability unlabeled examples as reliable anchors improves accuracy and enables finer object relations among new classes.
In this paper, we tackle the problem of discovering new classes in unlabeled visual data given labeled data from disjoint classes. Existing methods typically first pre-train a model with labeled data, and then identify new classes in unlabeled data via unsupervised clustering. However, the labeled data that provide essential knowledge are often underexplored in the second step. The challenge is that the labeled and unlabeled examples are from non-overlapping classes, which makes it difficult to build a learning relationship between them. In this work, we introduce Open-Mix to mix the unlabeled examples from an open set and the labeled examples from known classes, where their non-overlapping labels and pseudo-labels are simultaneously mixed into a joint label distribution. OpenMix dynamically compounds examples in two ways. First, we produce mixed training images by incorporating labeled examples with unlabeled examples. With the benefit of unique prior knowledge in novel class discovery, the generated pseudo-labels will be more credible than the original unlabeled predictions. As a result, OpenMix helps preventing the model from overfitting on unlabeled samples that may be assigned with wrong pseudo-labels. Second, the first way encourages the unlabeled examples with high class-probabilities to have considerable accuracy. We introduce these examples as reliable anchors and further integrate them with unlabeled samples. This enables us to generate more combinations in unlabeled examples and exploit finer object relations among the new classes. Experiments on three classification datasets demonstrate the effectiveness of the proposed OpenMix, which is superior to state-of-the-art methods in novel class discovery.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据