Enhancing Robustness of Implicit Neural Representations Against Weight Perturbations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916907825758208 |
|---|---|
| author | Zhou, Wenyong Cheng, Yuxin Liu, Zhengwu Wu, Taiqiang Zhang, Chen Wong, Ngai |
| author_facet | Zhou, Wenyong Cheng, Yuxin Liu, Zhengwu Wu, Taiqiang Zhang, Chen Wong, Ngai |
| contents | Implicit Neural Representations (INRs) encode discrete signals in a continuous manner using neural networks, demonstrating significant value across various multimedia applications. However, the vulnerability of INRs presents a critical challenge for their real-world deployments, as the network weights might be subjected to unavoidable perturbations. In this work, we investigate the robustness of INRs for the first time and find that even minor perturbations can lead to substantial performance degradation in the quality of signal reconstruction. To mitigate this issue, we formulate the robustness problem in INRs by minimizing the difference between loss with and without weight perturbations. Furthermore, we derive a novel robust loss function to regulate the gradient of the reconstruction loss with respect to weights, thereby enhancing the robustness. Extensive experiments on reconstruction tasks across multiple modalities demonstrate that our method achieves up to a 7.5~dB improvement in peak signal-to-noise ratio (PSNR) values compared to original INRs under noisy conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_13481 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Robustness of Implicit Neural Representations Against Weight Perturbations Zhou, Wenyong Cheng, Yuxin Liu, Zhengwu Wu, Taiqiang Zhang, Chen Wong, Ngai Computer Vision and Pattern Recognition Implicit Neural Representations (INRs) encode discrete signals in a continuous manner using neural networks, demonstrating significant value across various multimedia applications. However, the vulnerability of INRs presents a critical challenge for their real-world deployments, as the network weights might be subjected to unavoidable perturbations. In this work, we investigate the robustness of INRs for the first time and find that even minor perturbations can lead to substantial performance degradation in the quality of signal reconstruction. To mitigate this issue, we formulate the robustness problem in INRs by minimizing the difference between loss with and without weight perturbations. Furthermore, we derive a novel robust loss function to regulate the gradient of the reconstruction loss with respect to weights, thereby enhancing the robustness. Extensive experiments on reconstruction tasks across multiple modalities demonstrate that our method achieves up to a 7.5~dB improvement in peak signal-to-noise ratio (PSNR) values compared to original INRs under noisy conditions. |
| title | Enhancing Robustness of Implicit Neural Representations Against Weight Perturbations |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.13481 |