论文标题
带有附带信息的语义压缩：率延伸的观点
Semantic Compression with Side Information: A Rate-Distortion Perspective
论文作者
论文摘要
我们考虑由以任务为导向的视频压缩动机的语义率延伸问题。与该任务相对应的语义信息（不可观察到编码器）通过联合概率分布对观察结果显示出影响。框架内段和视频压缩中的框架之间的相似性是在编码器和解码器上可用的侧面信息。解码器有兴趣在某些失真约束下恢复观察并推断语义信息。我们通过充分表征率延伸功能来建立压缩率和扭曲之间权衡的信息理论限制。我们进一步评估了三种情况下的特定马尔可夫条件下的速率延伸功能：i）任务和观察都是二进制来源； ii）任务是整数观察结果均匀而奇怪的二元分类； iii）高斯相关的任务和观察。我们还通过数值结果来说明，与恢复源观察相比，仅恢复语义信息可以降低编码率。
We consider the semantic rate-distortion problem motivated by task-oriented video compression. The semantic information corresponding to the task, which is not observable to the encoder, shows impacts on the observations through a joint probability distribution. The similarities among intra-frame segments and inter-frames in video compression are formulated as side information available at both the encoder and the decoder. The decoder is interested in recovering the observation and making an inference of the semantic information under certain distortion constraints. We establish the information-theoretic limits for the tradeoff between compression rates and distortions by fully characterizing the rate-distortion function. We further evaluate the rate-distortion function under specific Markov conditions for three scenarios: i) both the task and the observation are binary sources; ii) the task is a binary classification of an integer observation as even and odd; iii) Gaussian correlated task and observation. We also illustrate through numerical results that recovering only the semantic information can reduce the coding rate comparing to recovering the source observation.
