AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Self-supervised Pre-training for Mirror Detection

Jiaying Lin, Rynson W.H. Lau

ICCV 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 8 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
add three-stage progressive SSL pre-training (image, patch, pixel) versus supervised ImageNet pre-trainingMirrorNet · MSD testF-measure: 0.727 -> 0.763Improved
add image-level pre-training only versus random init (ablation)MirrorNet · MSD testF-measure: 0.601 -> 0.623No clear effect
add patch-level pre-training versus random init (ablation)MirrorNet · MSD testF-measure: 0.601 -> 0.689Improved
add image-level stage to patch-level pre-training (ablation)MirrorNet · MSD testF-measure: 0.689 -> 0.723Improved
add pixel-level stage to patch-level pre-training (ablation)MirrorNet · MSD testMAE: 0.162 -> 0.124Improved
add image-level stage to patch + pixel pre-training (ablation)MirrorNet · MSD testF-measure: 0.758 -> 0.763Improved
add location predictor in patch-level stage (ablation)MirrorNet · MSD testF-measure: 0.731 -> 0.763Improved
train the three stages sequentially instead of in parallel (ablation)MirrorNet · MSD testMAE: 0.331 -> 0.116Improved
increase pre-training iterations beyond 20,000 per stage (ablation)SSL pre-training framework · MSD testF-measureHurt
use our SSL pre-training instead of generic SSL methods on VCNetVCNet · MSD testF-measure: 0.857 -> 0.886Improved

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