- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
Building on the observation from COSMO-INR that odd/even symmetric activation functions have alternating zero Chebyshev coefficients, which may lead to spectral attenuation, the authors propose a real-valued nonlinear phase expansion, NOPE: where the quadratic term breaks the symmetry and the cubic term ensures monotonicity of the phase map. Based on this formulation, the authors further introduce the NASA activation. The method is evaluated mainly on image-related INR tasks, including image fitting on nine selected Kodak images, as well as single-image inpainting, super-resolution, and denoising. The paper also provides an NTK analysis and visualization.
Critical strengths
- The experimental results on image-related tasks are strong.
- The derivation showing how the cubic term prevents phase folding is clear.
Critical weaknesses
-
I have concerns about the main motivation based on activation symmetry. SIREN/FINER activations are indeed odd as scalar functions of their pre-activation input. However, an actual neuron takes as input to the activation, and with a nonzero bias, is no longer an odd function of . And the oddness of the activation itself does not imply a lack of completeness or insufficient representation capacity. Therefore, it is unclear to me whether the alternating-zero Chebyshev coefficients of the scalar activation constitute a meaningful limitation at the network level.
-
The experiments are currently focused mainly on images. At least, I believe the full results on all 24 Kodak images should be reported in the supplementary material, since this evaluation is inexpensive. More broadly, INR methods can naturally be evaluated on more modalities, as the authors themselves state: “This approach has been applied to audio, images, 3D objects, and high-dimensional signals.” Moreover, compared with the baselines, the proposed design introduces several changes simultaneously, including the tanh window, the asymmetric phase, and the learnable parameters. A causal ablation study is needed to see which component is responsible for the improvement.
Questions for authors
-
What are the individual contributions of the window function, the asymmetric phase, and the learnable activation parameters?
-
How does NASA compare with COSMO-INR under the same experimental setting?
-
What are the mean and variance over all 24 Kodak images using at least three random seeds?