# Faster-LTN: a neuro-symbolic, end-to-end object detection architecture

Source: [Faster-LTN: a neuro-symbolic, end-to-end object detection architecture](<https://www.sota2.com/research/paper/68fa6acb1e209131cea2a4d6>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:33:16.767Z

Authors: Francesco Manigrasso, Filomeno Davide Miro, Lia Morra, Fabrizio Lamberti

Published: 2021-07-05T09:09:20.000Z

## Abstract

The detection of semantic relationships between objects represented in an image is one of the fundamental challenges in image interpretation. Neural-Symbolic techniques, such as Logic Tensor Networks (LTNs), allow the combination of semantic knowledge representation and reasoning with the ability to efficiently learn from examples typical of neural networks. We here propose Faster-LTN, an object detector composed of a convolutional backbone and an LTN. To the best of our knowledge, this is the first attempt to combine both frameworks in an end-to-end training setting. This architecture is trained by optimizing a grounded theory which combines labelled examples with prior knowledge, in the form of logical axioms. Experimental comparisons show competitive performance with respect to the traditional Faster R-CNN architecture.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2107.01877>)

[PDF](<https://arxiv.org/pdf/2107.01877.pdf>)
