AI Paper Atlas

Research map / Architectures and efficiency / Quantization

ORFC: Orthogonal Reparameterization for Low-Bitrate ViT Feature Coding

Letian Zhang, Wenhan Yang, Lingyu Duan

ECCV 2026 · Architectures and efficiency › Quantization · approach: Post-training quantization of ViTs · 0 citations (OpenAlex)

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
learn an orthogonal rotation under output-deviation loss before grouped PQ (ablation)ORFC · DINOv2 ViT-L/14 block 20 segmentationBD-rate vs VTM (%): 14.4% -> -41.4%Improved
learn an orthogonal rotation under output-deviation loss before grouped PQ (ablation)ORFC · DINOv2 ViT-L/14 block 20 classificationBD-rate vs VTM (%): -57.0% -> -77.5%Improved
use frozen-tail output deviation Lref instead of feature-space MSE as distortion (ablation)ORFC · DINOv2 ViT-L/14 block 20 segmentationBD-rate vs VTM (%): 153.2% -> -41.4%Improved
use frozen-tail output deviation Lref instead of feature-space MSE as distortion (ablation)ORFC · DINOv2 ViT-L/14 block 20 classificationBD-rate vs VTM (%): -5.2% -> -77.5%Improved
add soft assignment with temperature annealing (ablation)ORFC · DINOv2 ViT-L/14 block 20 segmentationBD-rate vs VTM (%): 181.2% -> -41.4%Improved
add soft assignment with temperature annealing (ablation)ORFC · DINOv2 ViT-L/14 block 20 classificationBD-rate vs VTM (%): -24.8% -> -77.5%Improved
ORFC vs OPQ at matched low bitrateDINOv2 ViT-L/14 block 10 · ImageNet clsAcc@1 (%): 34.2 -> 96.0Improved
ORFC vs OPQ and VTM at low bitrateVitDet ViT-B/16 block 3 · COCO2017 detectionmAP@0.5:0.95 (%): 36.7 -> 91.6 (OPQ), 49.5 -> 91.6 (VTM)Improved
ORFC vs VTM on deeper layersDINOv2 ViT-L/14 · VOC2012 segBD-rate vs VTM (%): -65.8 (blk10) vs -41.4 (blk20)Mixed
MSE-driven rotation (OPQ) instead of task-aligned rotationgrouped PQ · DINOv2 ViT-L/14 block 20 group-wise sensitivityimbalance of per-group accuracy gainNo clear effect

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