Pith. sign in

Improved techniques for quantizing deep networks with adaptive bit-widths,

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Nearly Lossless Adaptive Bit Switching

cs.CV · 2025-02-03 · conditional · novelty 5.0

Double Rounding derives lower-bit neural network weights from a stored 8-bit integer model, achieving accuracy comparable to state-of-the-art multi-precision quantization on ImageNet.

citing papers explorer

Showing 1 of 1 citing paper.

  • Nearly Lossless Adaptive Bit Switching cs.CV · 2025-02-03 · conditional · none · ref 8

    Double Rounding derives lower-bit neural network weights from a stored 8-bit integer model, achieving accuracy comparable to state-of-the-art multi-precision quantization on ImageNet.