Alexander Radne och Erik Forsberg, MPCAS
Vectorization of architectural floor plans
PixMax – a semi-supervised approach to domain adaptation through pseudolabelling
Examiner: Fredrik Kahl, Dept of Electrical Engineering
Machine Learning and Computer Vision techniques are rapidly improving computers' abilities of image comprehension. In recent years, these techniques have been applied to information parsing on floor plan bitmap images, thus addressing the problem of converting rasterized images to vector graphics. Current state of the art models have shown great results in predicting walls as well as room types and architectural drawing icons. However, these models require a large amount of annotated data, and since the cost of labelling can be quite high, the current available datasets are limited in terms of diversity of styles and regional-specific features. Therefore, there is an opportunity for algorithms that exploit unlabelled data to further improve these models. Semi-supervised learning is a set of algorithms commonly used to achieve this.
We propose and analyse three approaches utilising semi-supervised learning through self-training by letting a model trained on labelled data make predictions on unlabelled data. We then use a collection of the best of these predictions as a basis for creating pseudolabels for further training. In the first approach, we use a probability measure on the model output as a proxy for high quality predictions. Our second approach is to use a post-processing algorithm as a quality enhancement of the predictions on all unannotated images. Finally we propose and evaluate our proposed prediction quality measurement, PixMax. This method aims to give a proxy for how confident the network is on its predictions by measuring inter-consistency between several non-destructive augmentations of any input image. The created pseudolabels are then compared to evaluate whether the network is confident enough or not for the pseudolabels to be included in the continued training.
With PixMax we obtain results comparable with --- and for recall better than --- the fully supervised state-of-the-art model that we benchmark against. Our evaluations are carried out both on the labelled and unlabelled dataset used to train the models. As expected, the relative performance boost is most prominent on the unlabelled dataset where we reach a 69% average recall. We show that the PixMax approach can be used for adapting a trained model to a new domain.
Student project presentation
29 January, 2021, 10:00
29 January, 2021, 11:00