The visual signal compression is a long-standing problem. Fueled by the recent advances of deep learning, exciting progress has been made. Despite better compression performance, existing end-to-end compression algorithms are still designed towards better signal quality in terms of rate-distortion optimization. In this paper, we show that the design and optimization of network architecture could be further improved for compression towards machine vision. We propose an inverted bottleneck structure for the encoder of the end-to-end compression towards machine vision, which specifically accounts for efficient representation of the semantic information. Moreover, we quest the capability of optimization by incorporating the analytics accuracy into the optimization process, and the optimality is further explored with generalized rate-accuracy optimization in an iterative manner. We use object detection as a showcase for end-to-end compression towards machine vision, and extensive experiments show that the proposed scheme achieves significant BD-rate savings in terms of analysis performance. Moreover, the promise of the scheme is also demonstrated with strong generalization capability towards other machine vision tasks, due to the enabling of signal-level reconstruction.
翻译:视觉信号压缩是一个长期存在的问题。 由最近深层学习的进步推动, 取得了令人振奋的进展。 尽管压缩性能有所改善, 现有的端到端压缩算法仍然在设计上, 在比例扭曲优化方面达到更好的信号质量。 在本文中, 我们显示网络结构的设计与优化可以进一步改进, 以便向机器视觉压缩。 我们为机器视觉端到端压缩的编码提议了一个倒置的瓶颈结构, 这具体体现了语义信息的有效表现。 此外, 我们还通过将分析性准确性纳入优化进程来追求优化能力, 并且进一步探索最佳性能, 以普遍的速率- 准确性优化方式进行迭接式的探索。 我们用物体探测作为向机器视觉的端到端压缩的示范, 并进行广泛的实验, 显示拟议的计划在分析性能方面实现了显著的BD- 率节减。 此外, 由于信号级重建的促成, 计划还表现出强大的普及能力, 也表现出了对其他机器视觉任务进行优化的能力。