Refine
Year of publication
Document Type
- Other (973) (remove)
Language
- English (677)
- German (279)
- Spanish (5)
- Italian (4)
- Multiple languages (4)
- Polish (2)
- French (1)
- Portuguese (1)
Keywords
- Arrayseismologie (5)
- array seismology (5)
- Dysphagie (4)
- E-Learning (4)
- Erdbeben (4)
- Judaism (4)
- Judentum (4)
- MOOC (4)
- Patholinguistik (4)
- Schluckstörung (4)
Institute
- Institut für Biochemie und Biologie (97)
- Institut für Physik und Astronomie (85)
- Hasso-Plattner-Institut für Digital Engineering GmbH (84)
- Institut für Geowissenschaften (76)
- Department Psychologie (46)
- Department Sport- und Gesundheitswissenschaften (46)
- Institut für Mathematik (46)
- Institut für Ernährungswissenschaft (32)
- Hasso-Plattner-Institut für Digital Engineering gGmbH (31)
- Institut für Chemie (30)
LoANs
(2019)
Recently, deep neural networks have achieved remarkable performance on the task of object detection and recognition. The reason for this success is mainly grounded in the availability of large scale, fully annotated datasets, but the creation of such a dataset is a complicated and costly task. In this paper, we propose a novel method for weakly supervised object detection that simplifies the process of gathering data for training an object detector. We train an ensemble of two models that work together in a student-teacher fashion. Our student (localizer) is a model that learns to localize an object, the teacher (assessor) assesses the quality of the localization and provides feedback to the student. The student uses this feedback to learn how to localize objects and is thus entirely supervised by the teacher, as we are using no labels for training the localizer. In our experiments, we show that our model is very robust to noise and reaches competitive performance compared to a state-of-the-art fully supervised approach. We also show the simplicity of creating a new dataset, based on a few videos (e.g. downloaded from YouTube) and artificially generated data.
In self-incompatible plants the female style rejects self pollen, yet the extent to which the female style in the many self-compatible species can still select between different pollen genotypes and thus bias fertilization success is unclear. A new study identifies the molecular basis for how styles of the self-compatible coyote tobacco bias the fertilization success of pollen genotypes using matching gene expression patterns in a manner analogous to cryptic female choice in animals.
Die DDR im Plural
(2023)