Extreme Compression of Adaptive Neural Images

• URL: http://arxiv.org/abs/2405.16807v2
• Date: Tue, 4 Jun 2024 18:42:01 GMT
• Title: Extreme Compression of Adaptive Neural Images
• Authors: Leo Hoshikawa, Marcos V. Conde, Takeshi Ohashi, Atsushi Irie,
• Abstract summary: Implicit Neural Representations (INRs) and Neural Fields are a novel paradigm for signal representation, from images and audio to 3D scenes and videos. We present a novel analysis on compressing neural fields, with the focus on images. We also introduce Adaptive Neural Images (ANI), an efficient neural representation that enables adaptation to different inference or transmission requirements.
• Score: 6.646501936980895
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Implicit Neural Representations (INRs) and Neural Fields are a novel paradigm for signal representation, from images and audio to 3D scenes and videos. The fundamental idea is to represent a signal as a continuous and differentiable neural network. This idea offers unprecedented benefits such as continuous resolution and memory efficiency, enabling new compression techniques. However, representing data as neural networks poses new challenges. For instance, given a 2D image as a neural network, how can we further compress such a neural image?. In this work, we present a novel analysis on compressing neural fields, with the focus on images. We also introduce Adaptive Neural Images (ANI), an efficient neural representation that enables adaptation to different inference or transmission requirements. Our proposed method allows to reduce the bits-per-pixel (bpp) of the neural image by 4x, without losing sensitive details or harming fidelity. We achieve this thanks to our successful implementation of 4-bit neural representations. Our work offers a new framework for developing compressed neural fields.

Related papers

• A Brain-Inspired Regularizer for Adversarial Robustness [25.57552719924835]
  Recent studies indicate that training CNNs with regularizers that promote brain-like representations, using neural recordings, can improve model robustness. We introduce a new regularizer that retains the essence of the original but is computed using image pixel similarities, eliminating the need for neural recordings. Our work explores how biologically motivated loss functions can be used to drive the performance of artificial neural networks.
  arXiv  Detail & Related papers  (2024-10-04T22:30:47Z)
• NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation [22.151167286623416]
  We propose an end-to-end NeRF compression framework that integrates non-linear transform, quantization, and entropy coding for memory-efficient scene representation. We demonstrate our method outperforms existing NeRF compression methods, enabling high-quality novel view synthesis with a memory budget of 0.5 MB.
  arXiv  Detail & Related papers  (2024-04-02T15:49:00Z)
• Graph Neural Networks for Learning Equivariant Representations of Neural Networks [55.04145324152541]
  We propose to represent neural networks as computational graphs of parameters. Our approach enables a single model to encode neural computational graphs with diverse architectures. We showcase the effectiveness of our method on a wide range of tasks, including classification and editing of implicit neural representations.
  arXiv  Detail & Related papers  (2024-03-18T18:01:01Z)
• Null Space Properties of Neural Networks with Applications to Image Steganography [6.063583864878311]
  The null space of a given neural network can tell us the part of the input data that makes no contribution to the final prediction. One application described here leads to a method of image steganography.
  arXiv  Detail & Related papers  (2024-01-01T03:32:28Z)
• Variable Bitrate Neural Fields [75.24672452527795]
  We present a dictionary method for compressing feature grids, reducing their memory consumption by up to 100x. We formulate the dictionary optimization as a vector-quantized auto-decoder problem which lets us learn end-to-end discrete neural representations in a space where no direct supervision is available.
  arXiv  Detail & Related papers  (2022-06-15T17:58:34Z)
• Neural Knitworks: Patched Neural Implicit Representation Networks [1.0470286407954037]
  We propose Knitwork, an architecture for neural implicit representation learning of natural images that achieves image synthesis. To the best of our knowledge, this is the first implementation of a coordinate-based patch tailored for synthesis tasks such as image inpainting, super-resolution, and denoising. The results show that modeling natural images using patches, rather than pixels, produces results of higher fidelity.
  arXiv  Detail & Related papers  (2021-09-29T13:10:46Z)
• Fast Training of Neural Lumigraph Representations using Meta Learning [109.92233234681319]
  We develop a new neural rendering approach with the goal of quickly learning a high-quality representation which can also be rendered in real-time. Our approach, MetaNLR++, accomplishes this by using a unique combination of a neural shape representation and 2D CNN-based image feature extraction, aggregation, and re-projection. We show that MetaNLR++ achieves similar or better photorealistic novel view synthesis results in a fraction of the time that competing methods require.
  arXiv  Detail & Related papers  (2021-06-28T18:55:50Z)
• Towards Understanding Hierarchical Learning: Benefits of Neural Representations [160.33479656108926]
  In this work, we demonstrate that intermediate neural representations add more flexibility to neural networks. We show that neural representation can achieve improved sample complexities compared with the raw input. Our results characterize when neural representations are beneficial, and may provide a new perspective on why depth is important in deep learning.
  arXiv  Detail & Related papers  (2020-06-24T02:44:54Z)
• Neural Sparse Representation for Image Restoration [116.72107034624344]
  Inspired by the robustness and efficiency of sparse coding based image restoration models, we investigate the sparsity of neurons in deep networks. Our method structurally enforces sparsity constraints upon hidden neurons. Experiments show that sparse representation is crucial in deep neural networks for multiple image restoration tasks.
  arXiv  Detail & Related papers  (2020-06-08T05:15:17Z)
• Non-linear Neurons with Human-like Apical Dendrite Activations [81.18416067005538]
  We show that a standard neuron followed by our novel apical dendrite activation (ADA) can learn the XOR logical function with 100% accuracy. We conduct experiments on six benchmark data sets from computer vision, signal processing and natural language processing.
  arXiv  Detail & Related papers  (2020-02-02T21:09:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.