AI Paper Atlas

Research map / Detection and segmentation / CNN features

Unsupervised Dense Prediction using Differentiable Normalized Cuts

Yanbin Liu, Stephen Gould

ECCV 2024 · Detection and segmentation › CNN features · approach: Plain and high-resolution ViTs · 2 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 structural regularization with horizontal, vertical and uniform mask templates (ablation)Differentiable NCut self-supervised dense learning · DUT-OMRON saliency, Simple post-processingIoU: 48.8 -> 56.4Improved
add the projector g (ablation)Differentiable NCut self-supervised dense learning · DUT-OMRON saliency, Simple post-processingIoU: 52.2 -> 56.4Improved
use NCut mask consistency loss instead of pixel-level consistency (ablation)Self-supervised dense learning · DUT-OMRON saliency, Simple post-processingIoU: 46.0 -> 56.4Improved
replace frozen DINO with the NCut-finetuned backbone in TokenCutTokenCut · DUT-OMRON saliencyIoU: 53.3 -> 55.7Improved
replace DINO backbone with finetuned backbone in MOVE and apply bilateral solverMOVE · DUT-OMRON and DUTS-TE saliency with bilateral solverIoU: DUT-OMRON 63.6 -> 63.0; DUTS-TE 68.7 -> 66.9; maxFbeta 73.4 -> 74.7 and 82.1 -> 83.7Mixed
apply finetuned backbone to object discovery post-processing methodsTokenCut, FOUND, MOST · VOC07 object discoveryCorLoc: 68.8 -> 71.3 (TokenCut); 72.5 -> 73.5 (FOUND); 74.8 -> 75.6 (MOST)Improved
finetune MAE and MoCoV3 with the framework for two epochsMAE ViT-B/16, MoCoV3 ViT-S/16 · Saliency, Simple post-processingaverage IoU: +8.7 (MAE), +9.9 (MoCoV3)Improved
finetune ResNet50 with the frameworkDINO ResNet50 · Saliency, Simple post-processingaverage IoU: +6.4Improved
replace DINO backbone with finetuned backbone for unsupervised semantic segmentationViT-S/16 on Pascal VOC12 · K=500 and K=21mIoU: 17.4 -> 19.0 (K=500); 4.6 -> 5.8 (K=21)Improved
finetune FOUND/MOVE backbones with the framework on ViT-S/8 (small saliency gains)MOVE · ECSSD saliencyIoU: 83.0 -> 83.1No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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