# Solving the Same-Different Task with Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2101.09129 · HTML: https://mlsanity.com/paper/2101.09129/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 22 Jan 2021.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [A simple neural network module for relational reasoning](https://mlsanity.com/paper/1706.01427/) (2017)
- [RAVEN: A Dataset for Relational and Analogical Visual rEasoNing](https://mlsanity.com/paper/1903.02741/) (2019)
- [Measuring abstract reasoning in neural networks](https://mlsanity.com/paper/1807.04225/) (2018)
- [Inferring and Executing Programs for Visual Reasoning](https://mlsanity.com/paper/1705.03633/) (2017)
- [Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning](https://mlsanity.com/paper/1803.05268/) (2018)
- [A Dataset and Architecture for Visual Reasoning with a Working Memory](https://mlsanity.com/paper/1803.06092/) (2018)
- [25 years of CNNs: Can we compare to human abstraction capabilities?](https://mlsanity.com/paper/1607.08366/) (2016)

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

- [Neither hype nor gloom do DNNs justice](https://mlsanity.com/paper/2312.05355/) (2023)
- [A Review of Emerging Research Directions in Abstract Visual Reasoning](https://mlsanity.com/paper/2202.10284/) (2022)
- [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)
- [Evaluating Compositional Scene Understanding in Multimodal Generative Models](https://mlsanity.com/paper/2503.23125/) (2025)
- [Beyond the limitations of any imaginable mechanism: large language models and psycholinguistics](https://mlsanity.com/paper/2303.00077/) (2023)
- [Visual Reasoning in Object-Centric Deep Neural Networks: A Comparative Cognition Approach](https://mlsanity.com/paper/2402.12675/) (2024)
- [Few-Shot Learning of Visual Compositional Concepts through Probabilistic Schema Induction](https://mlsanity.com/paper/2505.09859/) (2025)
- [The role of object-centric representations, guided attention, and external memory on generalizing visual relations](https://mlsanity.com/paper/2304.07091/) (2023)
- [Fixing the problems of deep neural networks will require better training data and learning algorithms](https://mlsanity.com/paper/2311.12819/) (2023)

## Abstract (arXiv)

Deep learning demonstrated major abilities in solving many kinds of different real-world problems in computer vision literature. However, they are still strained by simple reasoning tasks that humans consider easy to solve. In this work, we probe current state-of-the-art convolutional neural networks on a difficult set of tasks known as the same-different problems. All the problems require the same prerequisite to be solved correctly: understanding if two random shapes inside the same image are the same or not. With the experiments carried out in this work, we demonstrate that residual connections, and more generally the skip connections, seem to have only a marginal impact on the learning of the proposed problems. In particular, we experiment with DenseNets, and we examine the contribution of residual and recurrent connections in already tested architectures, ResNet-18, and CorNet-S respectively. Our experiments show that older feed-forward networks, AlexNet and VGG, are almost unable to learn the proposed problems, except in some specific scenarios. We show that recently introduced architectures can converge even in the cases where the important parts of their architecture are removed. We finally carry out some zero-shot generalization tests, and we discover that in these scenarios residual and recurrent connections can have a stronger impact on the overall test accuracy. On four difficult problems from the SVRT dataset, we can reach state-of-the-art results with respect to the previous approaches, obtaining super-human performances on three of the four problems.