# Deep Neural Networks Can Learn Generalizable Same-Different Visual Relations

arXiv: https://arxiv.org/abs/2310.09612 · HTML: https://mlsanity.com/paper/2310.09612/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 55 references that are in the map.
- First posted on arXiv 14 Oct 2023.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Progress measures for grokking via mechanistic interpretability](https://mlsanity.com/paper/2301.05217/) (2023)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)](https://mlsanity.com/paper/2205.01397/) (2022)
- [Are Convolutional Neural Networks or Transformers more like human vision?](https://mlsanity.com/paper/2105.07197/) (2021)
- [Abstraction and Analogy-Making in Artificial Intelligence](https://mlsanity.com/paper/2102.10717/) (2021)
- [Emergent Symbols through Binding in External Memory](https://mlsanity.com/paper/2012.14601/) (2020)
- [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)
- [Knowledge Matters: Importance of Prior Information for Optimization](https://mlsanity.com/paper/1301.4083/) (2013)
- [Relational reasoning and generalization using non-symbolic neural networks](https://mlsanity.com/paper/2006.07968/) (2020)
- [25 years of CNNs: Can we compare to human abstraction capabilities?](https://mlsanity.com/paper/1607.08366/) (2016)
- [A Developmentally-Inspired Examination of Shape versus Texture Bias in Machines](https://mlsanity.com/paper/2202.08340/) (2022)
- [Recurrent Vision Transformer for Solving Visual Reasoning Problems](https://mlsanity.com/paper/2111.14576/) (2021)

## Built on by (most cited first, 4 of 4)

- [Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects](https://mlsanity.com/paper/2406.15955/) (2024)
- [Visual Reasoning in Object-Centric Deep Neural Networks: A Comparative Cognition Approach](https://mlsanity.com/paper/2402.12675/) (2024)
- [Convolutional Neural Networks Can (Meta-)Learn the Same-Different Relation](https://mlsanity.com/paper/2503.23212/) (2025)
- [Feature, Alignment, and Supervision in Category Learning: A Comparative Approach with Children and Neural Networks](https://mlsanity.com/paper/2602.03124/) (2026)

## Abstract (arXiv)

Although deep neural networks can achieve human-level performance on many object recognition benchmarks, prior work suggests that these same models fail to learn simple abstract relations, such as determining whether two objects are the same or different. Much of this prior work focuses on training convolutional neural networks to classify images of two same or two different abstract shapes, testing generalization on within-distribution stimuli. In this article, we comprehensively study whether deep neural networks can acquire and generalize same-different relations both within and out-of-distribution using a variety of architectures, forms of pretraining, and fine-tuning datasets. We find that certain pretrained transformers can learn a same-different relation that generalizes with near perfect accuracy to out-of-distribution stimuli. Furthermore, we find that fine-tuning on abstract shapes that lack texture or color provides the strongest out-of-distribution generalization. Our results suggest that, with the right approach, deep neural networks can learn generalizable same-different visual relations.