JA-SIREN: Deterministic Initialization for Sinusoidal Networks via Spectral Matching
Quick Answer
JA-SIREN introduces a deterministic initialization for sinusoidal networks, eliminating stochastic variability and achieving a mean PSNR of 67.18 dB on the Kodak dataset, outperforming the best baseline by 21.30 dB.
Quick Take
JA-SIREN introduces a deterministic initialization for sinusoidal networks, eliminating stochastic variability and achieving a mean PSNR of 67.18 dB on the Kodak dataset, outperforming the best baseline by 21.30 dB. This method ensures reproducibility in scientific computing by using spectral analysis for weight initialization without random seeds.
Key Points
- JA-SIREN achieves zero run-to-run variance in performance.
- The method uses Discrete Sine Transform for weight computation.
- Closed-form weights analytically match the initial spectral response.
- Significant improvement in image regression consistency for INRs.
- No hyperparameter tuning required for initialization.
Article Content
From source RSS / original summaryarXiv:2606. 06671v1 Announce Type: new Abstract: Existing implicit neural representation (INR) approaches suffer from stochastic initialization that does not guarantee consistent or high-quality performance across runs, with variations reaching more than 2. 5 dB (78%) in image regression. This variation is problematic for scientific computing and simulation, where result reproducibility is crucial.
To address this problem, we present Jacobi-Anger Sinusoidal Representation Network (JA-SIREN), a deterministic initialization scheme for sinusoidal networks grounded in classical spectral analysis. By computing the Discrete Sine Transform (DST) of the target signal and leveraging the Jacobi-Anger expansion, we derive closed-form weights for a two-layer sinusoidal MLP that analytically match the network's initial spectral response to the target signal, requiring no random seed or additional hyperparameter tuning.
On the Kodak dataset, JA-SIREN achieves a mean PSNR of 67. 18 dB, a 21. 30 dB improvement over the best baseline. This is achieved with zero run-to-run variance, confirming that spectrally-informed initialization is a more effective and reproducible alternative to stochastic initialization for sinusoidal INRs.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
A phase-aware LLM agent optimizes human-object interaction retrieval, outperforming Optuna TPE by 33.3% and VDTuner by 34.2% on the HICO-DET benchmark. This method enhances throughput by 15.3x over UniIR and demonstrates strong transferability across vector database management systems.