AI Paper Atlas

Research map / Video / Video segmentation and tracking

Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation

Mingmin Zhen, Shiwei Li, Lei Zhou, Jiaxiang Shang, Haoan Feng, Tian Fang, Long Quan

ECCV 2020 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 68 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 DFM and ATM (discriminative features with attention) (ablation)DeepLabv3 baseline · DAVIS16J mean: 76.7 -> 79.5Improved
add CRF refinement of attention map (ablation)DFNet · DAVIS16J mean: 79.5 -> 80.4Improved
add multiple-scale inference (ablation)DFNet · DAVIS16J mean: 80.4 -> 81.1Improved
add instance pruning post-processing (ablation)DFNet · DAVIS16J mean: 81.1 -> 83.4Improved
increase number of D-features from 128 to 2048 (ablation)DFNet · DAVIS16J mean: 78.3 -> 80.4Improved
increase number of D-features from 128 to 256 (ablation)DFNet · DAVIS16J mean: 78.3 -> 79.0Improved
increase input images at inference from 1 to 4 (ablation)DFNet · DAVIS16J mean: 79.4 -> 80.4Improved
increase input images from 4 to 10 (ablation)DFNet · DAVIS16J mean: 80.4 -> 80.4No clear effect
increase input images at inference from 1 to 8 (ablation)DFNet · PASCAL VOC co-segmentationAvg. J (%): 61.4 -> 65.4Improved
increase input images from 8 to 10 (ablation)DFNet · PASCAL VOC co-segmentationAvg. J (%): 65.4 -> 65.4No clear effect
use DFNet instead of AnDiffAnDiff · DAVIS16 testJ mean: 81.7 -> 83.4Improved
use DFNet instead of Li19 for co-segmentationLi19 · PASCAL VOC co-segmentationJaccard index: 0.63 -> 0.69Improved

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