# Same-different problems strain convolutional neural networks

arXiv: https://arxiv.org/abs/1802.03390 · HTML: https://mlsanity.com/paper/1802.03390/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Feb 2018.

## Built on by (most cited first, 6 of 6)

- [A Review of Emerging Research Directions in Abstract Visual Reasoning](https://mlsanity.com/paper/2202.10284/) (2022)
- [Systematic Visual Reasoning through Object-Centric Relational Abstraction](https://mlsanity.com/paper/2306.02500/) (2023)
- [Slot Abstractors: Toward Scalable Abstract Visual Reasoning](https://mlsanity.com/paper/2403.03458/) (2024)
- [Arguments for the Unsuitability of Convolutional Neural Networks for Non--Local Tasks](https://mlsanity.com/paper/2102.11944/) (2021)
- [RESOLVE: Relational Reasoning with Symbolic and Object-Level Features Using Vector Symbolic Processing](https://mlsanity.com/paper/2411.08290/) (2024)
- [LARS-VSA: A Vector Symbolic Architecture For Learning with Abstract Rules](https://mlsanity.com/paper/2405.14436/) (2024)

## Abstract (arXiv)

The robust and efficient recognition of visual relations in images is a hallmark of biological vision. We argue that, despite recent progress in visual recognition, modern machine vision algorithms are severely limited in their ability to learn visual relations. Through controlled experiments, we demonstrate that visual-relation problems strain convolutional neural networks (CNNs). The networks eventually break altogether when rote memorization becomes impossible, as when intra-class variability exceeds network capacity. Motivated by the comparable success of biological vision, we argue that feedback mechanisms including attention and perceptual grouping may be the key computational components underlying abstract visual reasoning.