Related Experiment Video
Updated: Jul 16, 2025
14:38
Creating Objects and Object Categories for Studying Perception and Perceptual Learning
Published on: November 2, 2012
11.9K
Human shape representations are not an emergent property of learning to classify objects.
Gaurav Malhotra1, Marin Dujmović1, John Hummel2
1School of Psychological Sciences, University of Bristol.
Journal of Experimental Psychology. General
|September 11, 2023
Summary
Humans are uniquely sensitive to object part relationships, unlike artificial neural networks. This sensitivity arises from inferring object properties, not just image classification learning.
Area of Science:
- Cognitive Science
- Computer Vision
- Psychology
Background:
- Humans exhibit a strong sensitivity to the relationships between object parts.
- The underlying reasons for this human sensitivity, particularly in object recognition, remain largely unexplained.
- A prominent hypothesis suggests that relational features are crucial for object categorization and develop through learning.
Purpose of the Study:
- To investigate whether supervised convolutional neural networks (CNNs) develop human-like sensitivity to relational changes in objects.
- To compare the internal representations and behavioral responses of CNNs and humans when exposed to object deformations.
- To determine if manipulating the learning environment to emphasize relational features enhances CNN sensitivity to these features.
Main Methods:
- Analyzing internal representations of supervised CNNs trained on large object datasets.
- Comparing human behavioral responses to object deformations with CNN sensitivity to the same changes.
- Testing CNN performance and sensitivity under modified learning conditions where relational information is made uniquely diagnostic.
Main Results:
- CNNs did not replicate the human sensitivity to relational changes in object parts.
- Human behavior was best predicted by the number of relational changes, whereas CNNs showed uniform sensitivity to all types of changes.
- Even when trained in environments where relations were uniquely diagnostic, CNNs did not develop a general sensitivity to relational changes.
Conclusions:
- Learning to classify objects is insufficient for artificial neural networks to develop human-like shape representations.
- Human sensitivity to relational changes appears to stem from inferring properties of distal objects from retinal images.
- This inferential process creates a qualitative difference between human object representations and those optimized for image classification in artificial neural networks.
More Related Videos
Related Concept Videos
02:13The Representativeness Heuristic
15.8K
The representative heuristic describes a biased way of thinking, in which you unintentionally stereotype someone or something. For example, you may assume that your professors spend their free time reading books and engaging in intellectual conversation, because the idea of them spending their time playing volleyball or visiting an amusement park does not fit in with your stereotypes of professors.
15.8K
01:24Concepts and Prototypes
177
The human nervous system handles vast amounts of information by translating sensory stimuli into neural impulses, which the brain processes, creating thoughts expressed through language or stored as memories. The brain also synthesizes information from emotions and memories, which significantly influence thoughts and behaviors. This intricate process creates a comprehensive mental picture.
The brain organizes this information using concepts, which are mental categories grouping linguistic data,...
The brain organizes this information using concepts, which are mental categories grouping linguistic data,...
177
01:20Structural Classification of Joints
3.5K
Joints, also known as articulations, are classified based on their structural characteristics, i.e., based on whether the articulating surfaces of the adjacent bones are directly connected by fibrous connective tissue or cartilage, or whether the articulating surfaces contact each other within a fluid-filled joint cavity. These differences serve to divide the joints of the body into three structural classifications.
A fibrous joint is where the adjacent bones are united by fibrous connective...
A fibrous joint is where the adjacent bones are united by fibrous connective...
3.5K
01:18Introduction to Learning
465
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
465
01:18Classification of Bones
5.7K
The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The...
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The...
5.7K
01:12Observational Learning
207
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
207