用自适应量化扩大卷积感受野，提升快速推理精度。
Receptive Field Expanded Look-Up Tables for Vision Inference: Advancing from Low-level to High-level Tasks
- 设计自适应格点量化的量化器，按数据重要性分配分辨率。
- 在固定表大小下实现多层级上下文信息捕捉，精度显著提升。
- 适合需要高速高精度推理的视觉任务部署场景。
近期多项查找表（LUT）方法通过空间换速度策略大幅加速CNN推理，但受限于卷积核感受野过小，因表格规模组合爆炸而难以扩展。本文旨在以固定表大小扩展CNN感受野，提升LUT驱动的快速推理性能，同时保持相同内存开销。核心贡献是提出一种新型最优格点向量量化器，能根据数据维度对推理任务的重要性自适应分配量化分辨率；相比当前常用的标量量化，该方法对卷积核有更精确的近似。此外，引入不规则空洞卷积和U型级联式LUT结构，无需增加表大小即可捕获多层次上下文信息。这些创新共同实现了速度、精度与内存效率的高效平衡，在多个任务上显著优于现有LUT方法。
原文摘要 · Abstract (English)
Recently, several look-up table (LUT) methods were developed to greatly expedite the inference of CNNs in a classical strategy of trading space for speed. However, these LUT methods suffer from a common drawback of limited receptive field of the convolution kernels due to the combinatorial explosion of table size. This research aims to expand the CNN receptive field with a fixed table size, thereby enhancing the performance of LUT-driven fast CNN inference while maintaining the same space complexity. To achieve this goal, various techniques are proposed. The main contribution is a novel approach of learning an optimal lattice vector quantizer that adaptively allocates the quantization resolution across data dimensions based on their significance to the inference task. In addition, the lattice vector quantizer offers an inherently more accurate approximation of CNN kernels than scalar quantizer as used in current practice. Furthermore, we introduce other receptive field expansion strategies, including irregular dilated convolutions and a U-shaped cascaded LUT structure, designed to capture multi-level contextual information without inflating table size. Together, these innovations allow our approach to effectively balance speed, accuracy, and memory efficiency, demonstrating significant improvements over existing LUT methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。