Logic Tensor Networks for Semantic Image Interpretation

Authors: Ivan Donadello, Luciano Serafini, Artur d'Avila Garcez

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 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-the-art Fast Region-based Convolutional Neural Networks (Fast R-CNN).
Researcher Affiliation Academia Ivan Donadello Fondazione Bruno Kessler and University of Trento Trento, Italy donadello@fbk.eu Luciano Serafini Fondazione Bruno Kessler Via Sommarive 18, I-38123 Trento, Italy serafini@fbk.eu Artur d Avila Garcez City, University of London Northampton Square London EC1V 0HB, UK a.garcez@city.ac.uk
Pseudocode No The paper does not include pseudocode or a clearly labeled algorithm block.
Open Source Code Yes LTN has been implemented as a Google TENSORFLOWT Mlibrary. Code, part Of ontology, and dataset are available at https://gitlab.fbk.eu/donadello/LTN_IJCAI17
Open Datasets Yes We use the PASCAL-PART-dataset that contains 10103 images with bounding boxes annotated with object-types and the part-of relation defined between pairs of bounding boxes. Labels are divided into three main groups: animals, vehicles and indoor objects, with their corresponding parts and partof label. ... The images were then split into a training set with 80%, and a test set with 20% of the images, maintaining the same proportion of the number of bounding boxes for each label.
Dataset Splits No The paper specifies a training and test set split but does not mention a separate validation set split.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU, GPU models, or memory) used for running the experiments.
Software Dependencies No LTN has been implemented as a Google TENSORFLOWT Mlibrary. While TENSORFLOW is mentioned, no specific version number for it or other software dependencies is provided.
Experiment Setup Yes The LTNs were set up with tensor of k = 6 layers and a regularization parameter λ = 10 10. We chose Lukasiewicz s T-norm (µ(a, b) = max(0, a + b 1)) and use the harmonic mean as aggregation operator. We ran 1000 training epochs of the RMSProp learning algorithm available in TENSORFLOWT M.