Related Experiment Video
Updated: Jun 5, 2026
14:38
Creating Objects and Object Categories for Studying Perception and Perceptual Learning
Published on: November 2, 2012
Learning a generative model of images by factoring appearance and shape
Nicolas Le Roux1, Nicolas Heess, Jamie Shotton
1Microsoft Research Cambridge, Machine Learning and Perception, Cambridge CB3 0FB, U.K. nicolas@le-roux.name.
Neural Computation
|December 18, 2010
Summary
This study introduces masked Restricted Boltzmann Machines (RBMs) to improve image understanding by modeling occlusion. This deep learning approach enhances computer vision models for tasks like segmentation and object recognition.
Area of Science:
- Computer Vision
- Machine Learning
- Deep Learning
Background:
- Computer vision has advanced significantly but still struggles to match human visual scene understanding.
- Existing models often lack the scope or power for comprehensive visual scene comprehension.
Purpose of the Study:
- To develop richer, more flexible image models by combining generative and hierarchical approaches.
- To introduce a novel model that explicitly handles occlusion boundaries in image patches.
Main Methods:
- Comparison of various Restricted Boltzmann Machines (RBMs) for continuous data.
- Introduction of the masked RBM (mRBM) that factors patch appearance from shape.
- Proposal of a generative model using a field of mRBMs for larger images.
Main Results:
- The masked RBM effectively models occlusion boundaries.
- A generative model using a field of mRBMs is proposed for larger image generation.
- Stacked masked RBMs can form deep models for complex structures.
Conclusions:
- Masked RBMs offer a promising step towards more capable image models.
- The proposed deep models are suitable for tasks like image segmentation and object recognition.
- This work advances the field of generative models in computer vision.
Related Concept Videos
01:14Steps in the Modeling Process
Albert Bandura's theory of observational learning identifies four critical processes: attention, retention, motor reproduction, and reinforcement or motivation.
Attention is the first necessary component for observational learning. It involves focusing on what the model is doing and saying. For example, if you decide to take a drawing class to enhance your skills, you need to pay close attention to the instructor's words and hand movements. The characteristics of the model significantly...
Attention is the first necessary component for observational learning. It involves focusing on what the model is doing and saying. For example, if you decide to take a drawing class to enhance your skills, you need to pay close attention to the instructor's words and hand movements. The characteristics of the model significantly...
01:21Gestalt Principles of Perception
Gestalt principles provide a framework for understanding how humans perceive objects as unified wholes within their context. These principles are essential in explaining the cognitive processes that make sense of complex visual stimuli by organizing them into coherent groups. One fundamental principle is proximity, which posits that objects located close to each other are perceived as a collective group. For instance, when dots are positioned near one another, the visual system interprets them...
01:27Associative Learning
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
Classical conditioning, also known...
01:18Introduction to Learning
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...
01:21Association Areas of the Cortex
Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
01:12Observational Learning
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 because...