Related Experiment Video
Updated: Aug 28, 2025
04:23
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
Published on: April 21, 2023
1.9K
Understanding transformation tolerant visual object representations in the human brain and convolutional neural
Yaoda Xu1, Maryam Vaziri-Pashkam2
1Psychology Department, Yale University, New Haven, CT 06520, USA.
Neuroimage
|September 18, 2022
Summary
Human brains exhibit robust object tolerance through functional smoothness, unlike convolutional neural networks (CNNs). This study reveals differences in how human visual systems and CNNs achieve transformation-tolerant object representations.
Area of Science:
- Neuroscience
- Computer Vision
- Cognitive Science
Background:
- Object recognition is crucial for primate vision, yet human tolerance mechanisms are not fully understood.
- Convolutional neural networks (CNNs) show human-like categorization but their tolerance development is unclear.
Purpose of the Study:
- To comprehensively compare object tolerance measures in the human brain and CNNs.
- To investigate how feature changes affect object representations in both systems.
Main Methods:
- fMRI was used to measure human brain responses to objects with Euclidean and non-Euclidean feature changes.
- Three tolerance measures (rank-order preservation, consistency, cross-decoding) were analyzed in human visual areas and eight CNNs.
Main Results:
- Human fMRI revealed robust object response rank-order preservation in higher visual areas, indicating functional smoothness.
- Object representational structure was highly consistent across feature changes in later ventral processing.
- These tolerance characteristics were absent in all tested CNNs, regardless of architecture or training data.
Conclusions:
- The human brain develops transformation-tolerant object representations with functional smoothness, particularly in higher visual areas.
- CNNs, despite high categorization performance, do not appear to develop similar tolerance mechanisms as the human brain.
- This research highlights key differences in visual processing between biological and artificial systems.
Related Concept Videos
01:24Vision
55.1K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
55.1K
01:26Visual System
658
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
Once through the pupil, the light passes through the lens, a...
658
01:01Neuroplasticity
703
Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.
703
01:25Neural Circuits
1.5K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.5K
01:20Parallel Processing
207
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
207
01:17Convolution Properties II
268
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
268