Efficient Feature Compression for Machines with Global Statistics Preservation
This work addresses the need for efficient feature compression in split-inference systems, such as those in MPEG standards, with incremental improvements over existing methods.
The paper tackles the problem of compressing intermediate feature data in split-inference AI models by proposing a method using Z-score normalization, which reduces bitrate by 17.09% on average and up to 65.69% for object tracking while maintaining task accuracy.
The split-inference paradigm divides an artificial intelligence (AI) model into two parts. This necessitates the transfer of intermediate feature data between the two halves. Here, effective compression of the feature data becomes vital. In this paper, we employ Z-score normalization to efficiently recover the compressed feature data at the decoder side. To examine the efficacy of our method, the proposed method is integrated into the latest Feature Coding for Machines (FCM) codec standard under development by the Moving Picture Experts Group (MPEG). Our method supersedes the existing scaling method used by the current standard under development. It both reduces the overhead bits and improves the end-task accuracy. To further reduce the overhead in certain circumstances, we also propose a simplified method. Experiments show that using our proposed method shows 17.09% reduction in bitrate on average across different tasks and up to 65.69% for object tracking without sacrificing the task accuracy.