A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918478485651456 |
|---|---|
| author | Montello, Fabio Güldenring, Ronja Scardapane, Simone Nalpantidis, Lazaros |
| author_facet | Montello, Fabio Güldenring, Ronja Scardapane, Simone Nalpantidis, Lazaros |
| contents | Model compression is essential in the deployment of large Computer Vision models on embedded devices. However, static optimization techniques (e.g. pruning, quantization, etc.) neglect the fact that different inputs have different complexities, thus requiring different amount of computations. Dynamic Neural Networks allow to condition the number of computations to the specific input. The current literature on the topic is very extensive and fragmented. We present a comprehensive survey that synthesizes and unifies existing Dynamic Neural Networks research in the context of Computer Vision. Additionally, we provide a logical taxonomy based on which component of the network is adaptive: the output, the computation graph or the input. Furthermore, we argue that Dynamic Neural Networks are particularly beneficial in the context of Sensor Fusion for better adaptivity, noise reduction and information prioritization. We present preliminary works in this direction. We complement this survey with a curated repository listing all the surveyed papers, each with a brief summary of the solution and the code base when available: https://github.com/DTU-PAS/awesome-dynn-for-cv . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_07451 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion Montello, Fabio Güldenring, Ronja Scardapane, Simone Nalpantidis, Lazaros Computer Vision and Pattern Recognition 68T45 I.4.0; I.2.10 Model compression is essential in the deployment of large Computer Vision models on embedded devices. However, static optimization techniques (e.g. pruning, quantization, etc.) neglect the fact that different inputs have different complexities, thus requiring different amount of computations. Dynamic Neural Networks allow to condition the number of computations to the specific input. The current literature on the topic is very extensive and fragmented. We present a comprehensive survey that synthesizes and unifies existing Dynamic Neural Networks research in the context of Computer Vision. Additionally, we provide a logical taxonomy based on which component of the network is adaptive: the output, the computation graph or the input. Furthermore, we argue that Dynamic Neural Networks are particularly beneficial in the context of Sensor Fusion for better adaptivity, noise reduction and information prioritization. We present preliminary works in this direction. We complement this survey with a curated repository listing all the surveyed papers, each with a brief summary of the solution and the code base when available: https://github.com/DTU-PAS/awesome-dynn-for-cv . |
| title | A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion |
| topic | Computer Vision and Pattern Recognition 68T45 I.4.0; I.2.10 |
| url | https://arxiv.org/abs/2501.07451 |