Implicit Neural Representation (INR) is an innovative approach for representing complex shapes or objects without explicitly defining their geometry or surface structure. Instead, INR represents objects as continuous functions. Previous research has demonstrated the effectiveness of using neural networks as INR for image compression, showcasing comparable performance to traditional methods such as JPEG. However, INR holds potential for various applications beyond image compression. This paper introduces Rapid-INR, a novel approach that utilizes INR for encoding and compressing images, thereby accelerating neural network training in computer vision tasks. Our methodology involves storing the whole dataset directly in INR format on a GPU, mitigating the significant data communication overhead between the CPU and GPU during training. Additionally, the decoding process from INR to RGB format is highly parallelized and executed on-the-fly. To further enhance compression, we propose iterative and dynamic pruning, as well as layer-wise quantization, building upon previous work. We evaluate our framework on the image classification task, utilizing the ResNet-18 backbone network and three commonly used datasets with varying image sizes. Rapid-INR reduces memory consumption to only 5% of the original dataset size and achieves a maximum 6$\times$ speedup over the PyTorch training pipeline, as well as a maximum 1.2x speedup over the DALI training pipeline, with only a marginal decrease in accuracy. Importantly, Rapid-INR can be readily applied to other computer vision tasks and backbone networks with reasonable engineering efforts. Our implementation code is publicly available at https://github.com/sharc-lab/Rapid-INR.

翻译：摘要：隐式神经表示（INR）是一种在不显式定义几何形状或表面结构的情况下，通过连续函数表征复杂形状或物体的创新方法。已有研究证实，将神经网络用作INR进行图像压缩具有与传统JPEG方法相当的性能。然而，INR在图像压缩之外的其他应用领域仍有巨大潜力。本文提出Rapid-INR，一种利用INR编码并压缩图像从而加速计算机视觉任务中神经网络训练的新方法。本方法通过将整个数据集直接以INR格式存储于GPU，显著缓解了训练过程中CPU与GPU间的数据通信开销。同时，从INR到RGB格式的解码过程采用高度并行化且即时执行的方式。为进一步提升压缩效率，我们在先前工作的基础上提出迭代式动态剪枝与层级量化技术。我们基于ResNet-18骨干网络及三种不同图像尺寸的常用数据集，在图像分类任务上评估了框架性能。Rapid-INR将内存消耗降至原始数据集大小的5%，较PyTorch训练流程实现最高6倍加速，较DALI训练流程实现最高1.2倍加速，且精度仅产生轻微下降。值得关注的是，通过适当的工程改造，Rapid-INR可便捷地应用于其他计算机视觉任务与骨干网络。我们的实现代码已开源至https://github.com/sharc-lab/Rapid-INR。