arXiv cs.AI
  • Score 81
  • Official

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

arXiv:2611.23445v1 Announce Type: new 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 wh

So what

What this event means by reading role—not a longer recap.

  • BuilderIf you ship quantized vision models to edge devices, budget 8-bit precision for late pointwise and depthwise layers and expect 1.48x-21.5x runtime slowdown from
  • ResearcherThis maps where sub-4-bit quantization collapse concentrates and quantifies a selective INT8 recovery waterfall on full ImageNet-1k validation.

Score dimensions

Higher total means read first. Each bar is one factor we use to rank the system pool. How we score

RelevanceHow tightly this is about AI.
78
ImpactHow much this could change the field or the market.
55
NoveltyHow new this is versus a recap.
62
CredibilityHow much we trust the source.
92
ActionabilityWhether a reader can do something with it.
60