Task-Aware Encoder Control for Deep Video Compression
This reduces the need for multiple decoders in deep video compression for machine tasks, offering a more flexible and efficient solution for applications like surveillance or autonomous systems.
The paper tackles the problem of needing separate deep video compression codecs for different machine tasks by introducing a task-aware encoder controller that adapts a single codec to tasks like detection and tracking, achieving about 25% bitrate reduction compared to prior methods.
Prior research on deep video compression (DVC) for machine tasks typically necessitates training a unique codec for each specific task, mandating a dedicated decoder per task. In contrast, traditional video codecs employ a flexible encoder controller, enabling the adaptation of a single codec to different tasks through mechanisms like mode prediction. Drawing inspiration from this, we introduce an innovative encoder controller for deep video compression for machines. This controller features a mode prediction and a Group of Pictures (GoP) selection module. Our approach centralizes control at the encoding stage, allowing for adaptable encoder adjustments across different tasks, such as detection and tracking, while maintaining compatibility with a standard pre-trained DVC decoder. Empirical evidence demonstrates that our method is applicable across multiple tasks with various existing pre-trained DVCs. Moreover, extensive experiments demonstrate that our method outperforms previous DVC by about 25% bitrate for different tasks, with only one pre-trained decoder.