Dataset Information

Dissociable Neural Representations of Adversarially Perturbed Images in Convolutional Neural Networks and the Human Brain.

ABSTRACT: Despite the remarkable similarities between convolutional neural networks (CNN) and the human brain, CNNs still fall behind humans in many visual tasks, indicating that there still exist considerable differences between the two systems. Here, we leverage adversarial noise (AN) and adversarial interference (AI) images to quantify the consistency between neural representations and perceptual outcomes in the two systems. Humans can successfully recognize AI images as the same categories as their corresponding regular images but perceive AN images as meaningless noise. In contrast, CNNs can recognize AN images similar as corresponding regular images but classify AI images into wrong categories with surprisingly high confidence. We use functional magnetic resonance imaging to measure brain activity evoked by regular and adversarial images in the human brain, and compare it to the activity of artificial neurons in a prototypical CNN-AlexNet. In the human brain, we find that the representational similarity between regular and adversarial images largely echoes their perceptual similarity in all early visual areas. In AlexNet, however, the neural representations of adversarial images are inconsistent with network outputs in all intermediate processing layers, providing no neural foundations for the similarities at the perceptual level. Furthermore, we show that voxel-encoding models trained on regular images can successfully generalize to the neural responses to AI images but not AN images. These remarkable differences between the human brain and AlexNet in representation-perception association suggest that future CNNs should emulate both behavior and the internal neural presentations of the human brain.

SUBMITTER: Zhang C

PROVIDER: S-EPMC8375771 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Recent studies suggest that deep Convolutional Neural Network (CNN) models show higher representational similarity, compared to any other existing object recognition models, with macaque inferior temporal (IT) cortical responses, human ventral stream fMRI activations and human object recognition. These studies employed natural images of objects. A long research tradition employed abstract shapes to probe the selectivity of IT neurons. If CNN models provide a realistic model of IT responses, then they should capture the IT selectivity for such shapes. Here, we compare the activations of CNN units to a stimulus set of 2D regular and irregular shapes with the response selectivity of macaque IT neurons and with human similarity judgements. The shape set consisted of regular shapes that differed in nonaccidental properties, and irregular, asymmetrical shapes with curved or straight boundaries. We found that deep CNNs (Alexnet, VGG-16 and VGG-19) that were trained to classify natural images show response modulations to these shapes that were similar to those of IT neurons. Untrained CNNs with the same architecture than trained CNNs, but with random weights, demonstrated a poorer similarity than CNNs trained in classification. The difference between the trained and untrained CNNs emerged at the deep convolutional layers, where the similarity between the shape-related response modulations of IT neurons and the trained CNNs was high. Unlike IT neurons, human similarity judgements of the same shapes correlated best with the last layers of the trained CNNs. In particular, these deepest layers showed an enhanced sensitivity for straight versus curved irregular shapes, similar to that shown in human shape judgments. In conclusion, the representations of abstract shape similarity are highly comparable between macaque IT neurons and deep convolutional layers of CNNs that were trained to classify natural images, while human shape similarity judgments correlate better with the deepest layers.

Dataset Information

Dissociable Neural Representations of Adversarially Perturbed Images in Convolutional Neural Networks and the Human Brain.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets