Towards Lossless Implicit Neural Representation via Bit Plane Decomposition
This work addresses the challenge of efficient and lossless data representation in machine learning, with applications in compression and quantization, though it appears incremental as it builds on existing INR methods.
The paper tackles the problem of achieving lossless implicit neural representations (INR) for high bit-depth signals by introducing a bit-plane decomposition method, which reduces the upper bound on model size and enables lossless fitting for 16-bit images and audio, previously unattainable.
We quantify the upper bound on the size of the implicit neural representation (INR) model from a digital perspective. The upper bound of the model size increases exponentially as the required bit-precision increases. To this end, we present a bit-plane decomposition method that makes INR predict bit-planes, producing the same effect as reducing the upper bound of the model size. We validate our hypothesis that reducing the upper bound leads to faster convergence with constant model size. Our method achieves lossless representation in 2D image and audio fitting, even for high bit-depth signals, such as 16-bit, which was previously unachievable. We pioneered the presence of bit bias, which INR prioritizes as the most significant bit (MSB). We expand the application of the INR task to bit depth expansion, lossless image compression, and extreme network quantization. Our source code is available at https://github.com/WooKyoungHan/LosslessINR