Albeit the scalable performance of vision transformers (ViTs), the dense
computational costs (training & inference) undermine their position in
industrial applications. Post-training quantization (PTQ), tuning ViTs with a
tiny dataset and running in a low-bit format, well addresses the cost issue but
unluckily bears more performance drops in lower-bit cases. In this paper, we
introduce I&S-ViT, a novel method that regulates the PTQ of ViTs in an
inclusive and stable fashion. I&S-ViT first identifies two issues in the PTQ of
ViTs: (1) Quantization inefficiency in the prevalent log2 quantizer for
post-Softmax activations; (2) Rugged and magnified loss landscape in
coarse-grained quantization granularity for post-LayerNorm activations. Then,
I&S-ViT addresses these issues by introducing: (1) A novel shift-uniform-log2
quantizer (SULQ) that incorporates a shift mechanism followed by uniform
quantization to achieve both an inclusive domain representation and accurate
distribution approximation; (2) A three-stage smooth optimization strategy
(SOS) that amalgamates the strengths of channel-wise and layer-wise
quantization to enable stable learning. Comprehensive evaluations across
diverse vision tasks validate I&S-ViT' superiority over existing PTQ of ViTs
methods, particularly in low-bit scenarios. For instance, I&S-ViT elevates the
performance of 3-bit ViT-B by an impressive 50.68%.

提出了一种新颖的方法 I&S-ViT，用于稳定地进行 ViTs 的 PTQ，包括引入 shift-uniform-log2 量化器（SULQ）和三阶段平滑优化策略（SOS），并通过对多样的视觉任务进行全面评估，证明了其在低位场景下相对于现有的 ViTs PTQ 方法的优越性。