跳到正文
arXiv cs.AI· Michael Schroeder·· 37 分钟前AI 评分38

为什么 4-bit 以下视觉 CNN 会崩溃:混合精度恢复的极限分析

Why Sub-4-Bit Vision CNNs Collapse and Where Mixed-Precision Recovery Stops

AI 导读

一项新研究系统分析了 ResNet、EfficientNet 等 Vision CNN 在 4-bit 以下量化时崩溃的机制,发现在 ImageNet-1k 5 万张验证集上,崩溃高度非线性,集中在后期 pointwise 投影和 depthwise 层。

正文 · 原文

View PDF HTML (experimental)

Abstract:Deep vision models operating in resource-constrained environments depend heavily on low-bit quantization, yet compressing weights below 4 bits frequently induces catastrophic accuracy collapse. While mixed-precision recovery strategies aim to rescue accuracy by selectively retaining high-precision parameters, the fundamental mechanics of where and why these models collapse remain poorly understood. In this study, we systematically analyze the anatomy of quantization collapse across standard Vision CNNs (including ResNet and EfficientNet backbones) evaluated on the full 50,000-image ImageNet-1k validation set. First, we map the exact progression of degradation, demonstrating that collapse is highly non-linear and concentrated in late-stage pointwise projections and depthwise layers. Second, we introduce a structured, multi-step recovery waterfall that evaluates selective integer precision (INT4/INT8) and selective floating-point scales. We show that keeping less than 5% of critical layer activations in 8-bit precision recovers up to 92% of the accuracy lost during aggressive sub-4-bit compression. Finally, we bridge the hardware reality gap by evaluating deployment performance on standard ARM and x86 CPU architectures. We show that while low-bit quantization reduces memory storage requirements, standard runtime software bit-unpacking introduces a 1.48x to 21.5x execution slowdown depending on batch size, highlighting a critical trade-off between model footprint and actual edge throughput. Our findings provide a practical blueprint for navigating the limits of sub-4-bit deployment without sacrificing hardware performance.
Comments: 8 pages, 6 figures, 2 tables
Subjects: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
Cite as: arXiv:2611.23445 [cs.AI]
  (or arXiv:2611.23445v2 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.23445

arXiv-issued DOI via DataCite

Submission history

From: Michael Schroeder [view email]
[v1] Tue, 17 Nov 2026 19:49:27 UTC (77 KB)
[v2] Thu, 19 Nov 2026 14:30:24 UTC (77 KB)

来源:arXiv cs.AI · arxiv.org