AI Paper Atlas

Research map / Image generation / Super-resolution

Mining self-similarity: Label super-resolution with epitomic representations

Nikolay Malkin, Anthony Ortiz, Nebojsa Jojic

ECCV 2020 · Image generation › Super-resolution · approach: Perceptual and real-world SR · 11 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
replace U-Net with epitome, both trained on South HR labelsSouth-trained segmentation · Chesapeake land cover (North region)overall accuracy (%): 59.4 -> 79.5Improved
increase self-epitomic tile size from 256^2 to 2048^2 (ablation)self-epitomic LSR · Chesapeake land cover (North region)overall accuracy (%): 85.9 -> 88.0Improved
increase self-epitomic tile size from 256^2 to 2048^2 (ablation)self-epitomic LSR · Chesapeake land cover (North region)mean IoU (%): 63.3 -> 67.8Improved
use whole-region (all-tile) epitome instead of 2048^2 tile (ablation)epitomic LSR · Chesapeake land cover (North region)overall accuracy (%): 88.0 -> 83.9Hurt
use 512^2 self-epitomic LSR instead of neural LSR trained with HR (S) and LR (N)LSR · Chesapeake land cover (North region)overall accuracy (%): 86.9 -> 87.0Improved
use epitomic LSR instead of U-Net neural LSR with LR (North) onlyLSR · Chesapeake land cover (North region)mean IoU (%): 41.3 -> 58.5Improved
add self-diversification to epitomic LSR (ablation)epitomic LSR · TIL segmentation (1786 labeled cell images)AUC: 0.794 -> 0.801Improved
use diversified epitomic LSR instead of CNN with pretrainingTIL detection · TIL segmentation (1786 labeled cell images)AUC: 0.786 -> 0.801Improved
ensemble color-only model with epitome model on shrubland and barren (ablation)GRSS LSR · GRSS 2020 Data Fusion validationaverage accuracy (%): 65.5 -> 68Improved
train small FCN on ensemble predictions (ablation)GRSS LSR · GRSS 2020 Data Fusion validationaverage accuracy (%): 68 -> 70.7Improved
use self-epitomic LSR instead of U-Net inferenceland cover · Land cover inference timems per thousand pixels: 3 -> 94Hurt

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