The Helmholtz Method: Using Perceptual Compression to Reduce Machine Learning Complexity
This addresses a key issue in multimedia computing and machine learning by showing how compression can enhance efficiency, though it is incremental in applying a physics reinterpretation to a known bottleneck.
The paper tackles the problem of whether perceptual compression artifacts harm machine learning performance, finding that at optimal quality levels, compression reduces complexity without hurting accuracy, and can even speed up training while maintaining or improving classification results.
This paper proposes a fundamental answer to a frequently asked question in multimedia computing and machine learning: Do artifacts from perceptual compression contribute to error in the machine learning process and if so, how much? Our approach to the problem is a reinterpretation of the Helmholtz Free Energy formula from physics to explain the relationship between content and noise when using sensors (such as cameras or microphones) to capture multimedia data. The reinterpretation allows a bit-measurement of the noise contained in images, audio, and video by combining a classifier with perceptual compression, such as JPEG or MP3. Our experiments on CIFAR-10 as well as Fraunhofer's IDMT-SMT-Audio-Effects dataset indicate that, at the right quality level, perceptual compression is actually not harmful but contributes to a significant reduction of complexity of the machine learning process. That is, our noise quantification method can be used to speed up the training of deep learning classifiers significantly while maintaining, or sometimes even improving, overall classification accuracy. Moreover, our results provide insights into the reasons for the success of deep learning.