# Visual Reasoning in Object-Centric Deep Neural Networks: A Comparative Cognition Approach

arXiv: https://arxiv.org/abs/2402.12675 · HTML: https://mlsanity.com/paper/2402.12675/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 30 of its 61 references that are in the map.
- First posted on arXiv 20 Feb 2024.

## Placed in

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

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [A simple neural network module for relational reasoning](https://mlsanity.com/paper/1706.01427/) (2017)
- [Emergent Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2212.09196/) (2022)
- [On the Binding Problem in Artificial Neural Networks](https://mlsanity.com/paper/2012.05208/) (2020)
- [Contrastive Learning of Structured World Models](https://mlsanity.com/paper/1911.12247/) (2019)
- [Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs](https://mlsanity.com/paper/1901.07017/) (2019)
- [Generalization and Robustness Implications in Object-Centric Learning](https://mlsanity.com/paper/2107.00637/) (2021)
- [Emergent Symbols through Binding in External Memory](https://mlsanity.com/paper/2012.14601/) (2020)
- [Complex-Valued Autoencoders for Object Discovery](https://mlsanity.com/paper/2204.02075/) (2022)
- [Neither hype nor gloom do DNNs justice](https://mlsanity.com/paper/2312.05355/) (2023)
- [Using Counterfactual Tasks to Evaluate the Generality of Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2402.08955/) (2024)
- [A Review of Emerging Research Directions in Abstract Visual Reasoning](https://mlsanity.com/paper/2202.10284/) (2022)
- [The Relational Bottleneck as an Inductive Bias for Efficient Abstraction](https://mlsanity.com/paper/2309.06629/) (2023)
- [On Neural Architecture Inductive Biases for Relational Tasks](https://mlsanity.com/paper/2206.05056/) (2022)
- [Systematic Visual Reasoning through Object-Centric Relational Abstraction](https://mlsanity.com/paper/2306.02500/) (2023)
- [Self-attention in Vision Transformers Performs Perceptual Grouping, Not Attention](https://mlsanity.com/paper/2303.01542/) (2023)
- [Contrastive Training of Complex-Valued Autoencoders for Object Discovery](https://mlsanity.com/paper/2305.15001/) (2023)
- [Understanding the computational demands underlying visual reasoning](https://mlsanity.com/paper/2108.03603/) (2021)
- [GAMR: A Guided Attention Model for (visual) Reasoning](https://mlsanity.com/paper/2206.04928/) (2022)
- [A Theory of Relation Learning and Cross-domain Generalization](https://mlsanity.com/paper/1910.05065/) (2019)
- [Solving the Same-Different Task with Convolutional Neural Networks](https://mlsanity.com/paper/2101.09129/) (2021)
- [Recurrent Vision Transformer for Solving Visual Reasoning Problems](https://mlsanity.com/paper/2111.14576/) (2021)
- [Affinity-based Attention in Self-supervised Transformers Predicts Dynamics of Object Grouping in Humans](https://mlsanity.com/paper/2306.00294/) (2023)
- [Deep Neural Networks Can Learn Generalizable Same-Different Visual Relations](https://mlsanity.com/paper/2310.09612/) (2023)
- [Arguments for the Unsuitability of Convolutional Neural Networks for Non--Local Tasks](https://mlsanity.com/paper/2102.11944/) (2021)

## Built on by (most cited first, 1 of 1)

- [Formalizing the Binding Problem](https://mlsanity.com/paper/2606.03976/) (2026)

## Abstract (arXiv)

Achieving visual reasoning is a long-term goal of artificial intelligence. In the last decade, several studies have applied deep neural networks (DNNs) to the task of learning visual relations from images, with modest results in terms of generalization of the relations learned. However, in recent years, object-centric representation learning has been put forward as a way to achieve visual reasoning within the deep learning framework. Object-centric models attempt to model input scenes as compositions of objects and relations between them. To this end, these models use several kinds of attention mechanisms to segregate the individual objects in a scene from the background and from other objects. In this work we tested relation learning and generalization in several object-centric models, as well as a ResNet-50 baseline. In contrast to previous research, which has focused heavily in the same-different task in order to asses relational reasoning in DNNs, we use a set of tasks -- with varying degrees of difficulty -- derived from the comparative cognition literature. Our results show that object-centric models are able to segregate the different objects in a scene, even in many out-of-distribution cases. In our simpler tasks, this improves their capacity to learn and generalize visual relations in comparison to the ResNet-50 baseline. However, object-centric models still struggle in our more difficult tasks and conditions. We conclude that abstract visual reasoning remains an open challenge for DNNs, including object-centric models.