Refine
Has Fulltext
- no (28)
Year of publication
- 2019 (28) (remove)
Document Type
- Other (17)
- Article (9)
- Part of a Book (1)
- Conference Proceeding (1)
Language
- English (28) (remove)
Is part of the Bibliography
- yes (28)
Keywords
- fabrication (2)
- 3D Point clouds (1)
- Association rule mining (1)
- Attention span (1)
- BIM (1)
- Biclustering (1)
- Blockchain (1)
- Bluetooth (1)
- Building Information Models (1)
- Close-Up (1)
- Cloud Computing (1)
- Cloud Storage Broker (1)
- Cloud access control and resource management (1)
- Commute pattern (1)
- Commute process (1)
- Coordinated and Multiple Views (1)
- Crowd-Resourcing (1)
- Cyber-Physical Systems (1)
- Data integration (1)
- Detail plus Overview (1)
- Eye-tracking (1)
- Facial mimicry (1)
- Feature selection (1)
- GPU-based Real-time Rendering (1)
- Gene expression (1)
- Geometry Draping (1)
- Geovisualization (1)
- Hidden Markov models (1)
- Human behaviour (1)
- IFC (1)
- Industry 4.0 (1)
- Industry Foundation Classes (1)
- Integrity Verification (1)
- Interactive Visualization (1)
- Internet of Things (1)
- Knowledge bases (1)
- Label analysis (1)
- Laser cutting (1)
- Learning behavior (1)
- Least privilege principle (1)
- Lecture video recording (1)
- Location-based services (1)
- Machine learning (1)
- Metamaterials (1)
- Mobile sensing (1)
- Natural language (1)
- Personal fabrication (1)
- Point-based rendering (1)
- Privilege separation concept (1)
- Process mining (1)
- Process model (1)
- Processing strategies (1)
- Real-time Rendering (1)
- Record linkage (1)
- Role-based access control (1)
- Self-aware computing systems (1)
- Social environment (1)
- Software Engineering (1)
- Temporal orientation (1)
- Terrain Visualization (1)
- Ubiquitous computing (1)
- Unified cloud model (1)
- Virtual Machine (1)
- Web-based rendering (1)
- algorithmic (1)
- change blindness (1)
- clustering (1)
- cognitive (1)
- complex emotions (1)
- computational design (1)
- data matching (1)
- deduplication (1)
- design thinking (1)
- digital identity (1)
- distributed ledger technology (1)
- e-Learning (1)
- e-lecture (1)
- electronic mail (1)
- emotional (1)
- empathy (1)
- entity resolution (1)
- evaluation (1)
- failure profile (1)
- game theory (1)
- identity management (1)
- inattentional blindness (1)
- interactive editing (1)
- laser cutting (1)
- network creation games (1)
- organizations (1)
- performance (1)
- portability (1)
- price of anarchy (1)
- prototypes (1)
- requirements engineering (1)
- reuse (1)
- self-healing (1)
- self-sovereign identity (1)
- simulator (1)
- software (1)
- staging (1)
- tools (1)
- tree conjecture (1)
- trust (1)
- virtual reality (1)
Institute
- Hasso-Plattner-Institut für Digital Engineering gGmbH (28) (remove)
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.