FGQ applies diagonal Fisher information to guide learnable affine transformations in PTQ for multi-task VGGT, yielding up to 39% relative gains over baselines at 4-bit quantization.
The same argument applies to discrete labels by replacing integrals with sums
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer
FGQ applies diagonal Fisher information to guide learnable affine transformations in PTQ for multi-task VGGT, yielding up to 39% relative gains over baselines at 4-bit quantization.