Same-different problems strain convolutional neural networks
This highlights a key limitation in machine vision for applications requiring abstract reasoning, such as robotics or medical imaging, and is incremental in identifying specific failure modes.
The study found that convolutional neural networks struggle with visual-relation tasks, breaking down when intra-class variability exceeds their capacity, as shown through controlled experiments.
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.\