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

arXiv: https://arxiv.org/abs/2107.01877 · HTML: https://mlsanity.com/paper/2107.01877/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 20 references that are in the map.
- First posted on arXiv 5 Jul 2021.

## Builds on (most cited first, 15 of 15)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Visual Relationship Detection with Language Priors](https://mlsanity.com/paper/1608.00187/) (2016)
- [Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding](https://mlsanity.com/paper/1810.02338/) (2018)
- [Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts](https://mlsanity.com/paper/1406.2031/) (2014)
- [Logic Tensor Networks](https://mlsanity.com/paper/2012.13635/) (2020)
- [Neural-Symbolic Learning and Reasoning: A Survey and Interpretation](https://mlsanity.com/paper/1711.03902/) (2017)
- [Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning](https://mlsanity.com/paper/1905.06088/) (2019)
- [Analyzing Differentiable Fuzzy Logic Operators](https://mlsanity.com/paper/2002.06100/) (2020)
- [Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective](https://mlsanity.com/paper/2003.00330/) (2020)
- [Logic Tensor Networks for Semantic Image Interpretation](https://mlsanity.com/paper/1705.08968/) (2017)
- [The More You Know: Using Knowledge Graphs for Image Classification](https://mlsanity.com/paper/1612.04844/) (2016)
- [From Statistical Relational to Neuro-Symbolic Artificial Intelligence](https://mlsanity.com/paper/2003.08316/) (2020)
- [An Explicitly Relational Neural Network Architecture](https://mlsanity.com/paper/1905.10307/) (2019)
- [Integrating Knowledge and Reasoning in Image Understanding](https://mlsanity.com/paper/1906.09954/) (2019)
- [Compensating Supervision Incompleteness with Prior Knowledge in Semantic Image Interpretation](https://mlsanity.com/paper/1910.00462/) (2019)

## Built on by (most cited first, 10 of 10)

- [Neuro-Symbolic Learning: Principles and Applications in Ophthalmology](https://mlsanity.com/paper/2208.00374/) (2022)
- [logLTN: Differentiable Fuzzy Logic in the Logarithm Space](https://mlsanity.com/paper/2306.14546/) (2023)
- [A Study on Neuro-Symbolic Artificial Intelligence: Healthcare Perspectives](https://mlsanity.com/paper/2503.18213/) (2025)
- [PROTOtypical Logic Tensor Networks (PROTO-LTN) for Zero Shot Learning](https://mlsanity.com/paper/2207.00433/) (2022)
- [Interval Logic Tensor Networks](https://mlsanity.com/paper/2303.17892/) (2023)
- [Fuzzy Logic Visual Network (FLVN): A neuro-symbolic approach for visual features matching](https://mlsanity.com/paper/2307.16019/) (2023)
- [Weakly Supervised Segmentation as Semantic-Based Regularization](https://mlsanity.com/paper/2605.13674/) (2026)
- [SymDQN: Symbolic Knowledge and Reasoning in Neural Network-based Reinforcement Learning](https://mlsanity.com/paper/2504.02654/) (2025)
- [Blog Data Showdown: Machine Learning vs Neuro-Symbolic Models for Gender Classification](https://mlsanity.com/paper/2512.16687/) (2025)
- [Learning to Reason: Targeted Knowledge Discovery and Fuzzy Logic Update for Robust Image Recognition](https://mlsanity.com/paper/2604.27759/) (2026)

## Abstract (arXiv)

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.