Can KAN Work? Exploring the Potential of Kolmogorov-Arnold Networks in Computer Vision
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910697031467008 |
|---|---|
| author | Cang, Yueyang liu, Yu hang Shi, Li |
| author_facet | Cang, Yueyang liu, Yu hang Shi, Li |
| contents | Kolmogorov-Arnold Networks(KANs), as a theoretically efficient neural network architecture, have garnered attention for their potential in capturing complex patterns. However, their application in computer vision remains relatively unexplored. This study first analyzes the potential of KAN in computer vision tasks, evaluating the performance of KAN and its convolutional variants in image classification and semantic segmentation. The focus is placed on examining their characteristics across varying data scales and noise levels. Results indicate that while KAN exhibits stronger fitting capabilities, it is highly sensitive to noise, limiting its robustness. To address this challenge, we propose a smoothness regularization method and introduce a Segment Deactivation technique. Both approaches enhance KAN's stability and generalization, demonstrating its potential in handling complex visual data tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_06727 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Can KAN Work? Exploring the Potential of Kolmogorov-Arnold Networks in Computer Vision Cang, Yueyang liu, Yu hang Shi, Li Computer Vision and Pattern Recognition Kolmogorov-Arnold Networks(KANs), as a theoretically efficient neural network architecture, have garnered attention for their potential in capturing complex patterns. However, their application in computer vision remains relatively unexplored. This study first analyzes the potential of KAN in computer vision tasks, evaluating the performance of KAN and its convolutional variants in image classification and semantic segmentation. The focus is placed on examining their characteristics across varying data scales and noise levels. Results indicate that while KAN exhibits stronger fitting capabilities, it is highly sensitive to noise, limiting its robustness. To address this challenge, we propose a smoothness regularization method and introduce a Segment Deactivation technique. Both approaches enhance KAN's stability and generalization, demonstrating its potential in handling complex visual data tasks. |
| title | Can KAN Work? Exploring the Potential of Kolmogorov-Arnold Networks in Computer Vision |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.06727 |