AHCQ-SAM introduces ACNR, HLUQ, CAG, and LNQ quantization techniques that deliver 15.2% mAP gain on 4-bit SAM-B and 14.01% J&F gain on 4-bit SAM2-Tiny versus prior PTQ methods.
Additive powers-of- two quantization: An efficient non-uniform discretization for neural networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
ShiftLIF maps membrane potentials to logarithmically spaced power-of-two spike levels, improving representational capacity in SNNs while keeping synaptic operations multiplier-free.
citing papers explorer
-
AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization
AHCQ-SAM introduces ACNR, HLUQ, CAG, and LNQ quantization techniques that deliver 15.2% mAP gain on 4-bit SAM-B and 14.01% J&F gain on 4-bit SAM2-Tiny versus prior PTQ methods.
-
ShiftLIF: Efficient Multi-Level Spiking Neurons with Power-of-Two Quantization
ShiftLIF maps membrane potentials to logarithmically spaced power-of-two spike levels, improving representational capacity in SNNs while keeping synaptic operations multiplier-free.