# Weakly Supervised Knowledge Transfer with Probabilistic Logical Reasoning for Object Detection

arXiv: https://arxiv.org/abs/2303.05148 · HTML: https://mlsanity.com/paper/2303.05148/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 23 of its 51 references that are in the map.
- First posted on arXiv 9 Mar 2023.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [A simple neural network module for relational reasoning](https://mlsanity.com/paper/1706.01427/) (2017)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018)
- [Weakly Supervised Deep Detection Networks](https://mlsanity.com/paper/1511.02853/) (2015)
- [End-to-End Differentiable Proving](https://mlsanity.com/paper/1705.11040/) (2017)
- [Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection](https://mlsanity.com/paper/1905.05396/) (2019)
- [DeepStochLog: Neural Stochastic Logic Programming](https://mlsanity.com/paper/2106.12574/) (2021)
- [Class-Incremental Domain Adaptation](https://mlsanity.com/paper/2008.01389/) (2020)
- [ROAD-R: The Autonomous Driving Dataset with Logical Requirements](https://mlsanity.com/paper/2210.01597/) (2022)
- [Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer](https://mlsanity.com/paper/2007.07986/) (2020)
- [Revisiting knowledge transfer for training object class detectors](https://mlsanity.com/paper/1708.06128/) (2017)
- [ChemGrapher: Optical Graph Recognition of Chemical Compounds by Deep Learning](https://mlsanity.com/paper/2002.09914/) (2020)
- [On learning to localize objects with minimal supervision](https://mlsanity.com/paper/1403.1024/) (2014)
- [Art2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-to-Image Translation](https://mlsanity.com/paper/1811.10666/) (2018)
- [Self-Labeling of Fully Mediating Representations by Graph Alignment](https://mlsanity.com/paper/2103.14133/) (2021)

## Built on by (most cited first, 3 of 3)

- [Atom-Level Optical Chemical Structure Recognition with Limited Supervision](https://mlsanity.com/paper/2404.01743/) (2024)
- [MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures](https://mlsanity.com/paper/2503.16096/) (2025)
- [Learning Predictive Checklists with Probabilistic Logic Programming](https://mlsanity.com/paper/2411.16790/) (2024)

## Abstract (arXiv)

Training object detection models usually requires instance-level annotations, such as the positions and labels of all objects present in each image. Such supervision is unfortunately not always available and, more often, only image-level information is provided, also known as weak supervision. Recent works have addressed this limitation by leveraging knowledge from a richly annotated domain. However, the scope of weak supervision supported by these approaches has been very restrictive, preventing them to use all available information. In this work, we propose ProbKT, a framework based on probabilistic logical reasoning that allows to train object detection models with arbitrary types of weak supervision. We empirically show on different datasets that using all available information is beneficial as our ProbKT leads to significant improvement on target domain and better generalization compared to existing baselines. We also showcase the ability of our approach to handle complex logic statements as supervision signal.