通过双流特征解耦实现高效的学得式数据压缩
Efficient Learned Data Compression via Dual-Stream Feature Decoupling
AI总结：
本文提出双流多尺度解耦器，通过解耦局部和全局上下文，替代深度串行处理，实现浅层并行流，并结合分层门控细化器，提升压缩效率与精度。
摘要：
尽管学得式数据压缩（LDC）已实现优异的压缩比，但平衡精确的概率建模与系统效率仍具挑战。关键在于，统一的单流架构难以同时捕捉微观语法和宏观语义特征，需深度串行堆叠，加剧延迟。此外，异构系统受限于设备速度不匹配，吞吐量受阿姆达尔定律限制。为此，我们提出双流多尺度解耦器，解耦局部和全局上下文以替代深度串行处理，采用分层门控细化器实现自适应特征细化与精确概率建模。此外，我们设计了并发流-并行流水线，克服系统瓶颈实现全流水线并行。大量实验表明，本文方法在压缩比和吞吐量上均达到最先进的性能，同时保持最低的延迟和内存使用。代码可在https://github.com/huidong-ma/FADE获取。
英文摘要：
While Learned Data Compression (LDC) has achieved superior compression ratios, balancing precise probability modeling with system efficiency remains challenging. Crucially, uniform single-stream architectures struggle to simultaneously capture micro-syntactic and macro-semantic features, necessitating deep serial stacking that exacerbates latency. Compounding this, heterogeneous systems are constrained by device speed mismatches, where throughput is capped by Amdahl's Law due to serial processing. To this end, we propose a Dual-Stream Multi-Scale Decoupler that disentangles local and global contexts to replace deep serial processing with shallow parallel streams, and incorporate a Hierarchical Gated Refiner for adaptive feature refinement and precise probability modeling. Furthermore, we design a Concurrent Stream-Parallel Pipeline, which overcomes systemic bottlenecks to achieve full-pipeline parallelism. Extensive experiments demonstrate that our method achieves state-of-the-art performance in both compression ratio and throughput, while maintaining the lowest latency and memory usage. The code is available at https://github.com/huidong-ma/FADE.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
