Investigating the Gestalt Principle of Closure in Deep Convolutional Neural Networks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915001811337216 |
|---|---|
| author | Zhang, Yuyan Soydaner, Derya Behrad, Fatemeh Koßmann, Lisa Wagemans, Johan |
| author_facet | Zhang, Yuyan Soydaner, Derya Behrad, Fatemeh Koßmann, Lisa Wagemans, Johan |
| contents | Deep neural networks perform well in object recognition, but do they perceive objects like humans? This study investigates the Gestalt principle of closure in convolutional neural networks. We propose a protocol to identify closure and conduct experiments using simple visual stimuli with progressively removed edge sections. We evaluate well-known networks on their ability to classify incomplete polygons. Our findings reveal a performance degradation as the edge removal percentage increases, indicating that current models heavily rely on complete edge information for accurate classification. The data used in our study is available on Github. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_00627 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Investigating the Gestalt Principle of Closure in Deep Convolutional Neural Networks Zhang, Yuyan Soydaner, Derya Behrad, Fatemeh Koßmann, Lisa Wagemans, Johan Computer Vision and Pattern Recognition Machine Learning Deep neural networks perform well in object recognition, but do they perceive objects like humans? This study investigates the Gestalt principle of closure in convolutional neural networks. We propose a protocol to identify closure and conduct experiments using simple visual stimuli with progressively removed edge sections. We evaluate well-known networks on their ability to classify incomplete polygons. Our findings reveal a performance degradation as the edge removal percentage increases, indicating that current models heavily rely on complete edge information for accurate classification. The data used in our study is available on Github. |
| title | Investigating the Gestalt Principle of Closure in Deep Convolutional Neural Networks |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2411.00627 |