AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Condition Number Based Low-Bit Quantization for Image Super-Resolution

Kai Liu, Dehui Wang, Zhiteng Li, Zheng Chen, Yong Guo, Linghe Kong

ICML 2026 · Architectures and efficiency › Quantization · approach: Post-training quantization of ViTs

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add condition number minimization of weights before quantization (ablation)2DQuant-based PTQ of SwinIR-light · Set5 x2 (2-bit)PSNR (dB): 37.08 -> 37.15Improved
use CondiQuant pipeline vs 2DQuantSwinIR-light 2-bit · Set5 x2PSNR (dB): 36.00 -> 37.15Improved
use CondiQuant vs 2DQuantSwinIR-light 2-bit · Set5 x4PSNR (dB): 29.53 -> 30.64Improved
quantize only activations vs only weights (ablation)SwinIR-light · Set5 x2PSNR (dB): 32.0117 (weights only) vs 31.3304 (activations only)Hurt
vary gradient step size eta from 1e-4 to 1e-1 (ablation)CondiQuant · Set5 x2 (2-bit)PSNR (dB): 37.08 - 37.15No clear effect
choose target value t as median or midpoint instead of mean (ablation)CondiQuant · Set5 x2 (2-bit)PSNR (dB): 37.15 -> 37.12 / 37.11No clear effect
vary regularization lambda from 0.001 to 0.010 (ablation)CondiQuant · Set5 x2 (2-bit)PSNR (dB): 37.15 (0.003) vs 37.08 (0.010)No clear effect
apply proximal condition number reductionSwinIR-light x2 weights · average condition numbercondition number: nearly 3k -> 28.37Improved
skip CondiQuant on FC1 and FC2 layers (ablation)CondiQuant · condition number analysisefficiencyNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy