Logic tensor networks for semantic image interpretation

Donadello, I., Serafini, L. & d'Avila Garcez, A. S. (2017). Logic tensor networks for semantic image interpretation. Paper presented at the IJCAI 2017, 19-25 Aug 2017, Melbourne, Australia.

Text - Accepted Version
Download (533kB) | Preview


Semantic Image Interpretation (SII) is the task of extracting structured semantic descriptions from images. It is widely agreed that the combined use of visual data and background knowledge is of great importance for SII. Recently, Statistical Relational Learning (SRL) approaches have been developed for reasoning under uncertainty and learning in the presence of data and rich knowledge. Logic Tensor Networks (LTNs) are a SRL framework which integrates neural networks with first-order fuzzy logic to allow (i) efficient learning from noisy data in the presence of logical constraints, and (ii) reasoning with logical formulas describing general properties of the data. In this paper, we develop and apply LTNs to two of the main tasks of SII, namely, the classification of an image's bounding boxes and the detection of the relevant part-of relations between objects. To the best of our knowledge, this is the first successful application of SRL to such SII tasks. The proposed approach is evaluated on a standard image processing benchmark. Experiments show that background knowledge in the form of logical constraints can improve the performance of purely data-driven approaches, including the state-of-theart Fast Region-based Convolutional Neural Networks (Fast R-CNN). Moreover, we show that the use of logical background knowledge adds robustness to the learning system when errors are present in the labels of the training data.

Item Type: Conference or Workshop Item (Paper)
Additional Information: © IJCAI, 2017. http://www.ijcai.org/
Uncontrolled Keywords: Machine Learning: Knowledge-based Learning; Robotics and Vision: Vision and Perception; Uncertainty in AI
Divisions: School of Informatics > Department of Computing
URI: http://openaccess.city.ac.uk/id/eprint/19151

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics