AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

MRF Optimization with Separable Convex Prior on Partially Ordered Labels

Csaba Domokos, Frank R. Schmidt, Daniel Cremers

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 4 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
use proposed coarse-to-fine separable convex prior method instead of FullFlow at 64x64 labelsoptical flow MRF optimization · MPI Sintel ambush 7 (64x64)runtime (s): 47.33 -> 0.89Improved
use proposed method instead of FullFlow at 64x64 labelsoptical flow MRF optimization · MPI Sintel ambush 7 (64x64)EPE: 0.65 -> 1.40Hurt
use proposed method instead of FullFlow at 8x8 labelsoptical flow MRF optimization · MPI Sintel sleeping 1 (8x8)runtime (s): 0.86 -> 0.35Improved
use proposed method instead of alpha-expansion at 64x64 labelsoptical flow MRF optimization · MPI Sintel ambush 7 (64x64)runtime (s): 286.73 -> 0.89Improved
use proposed method instead of alpha-expansion at 64x64 labelsoptical flow MRF optimization · MPI Sintel ambush 7 (64x64)EPE: 1.36 -> 1.40Hurt
use proposed method instead of Shekhovtsov et al. [12]optical flow MRF optimization · MPI Sintel ambush 7 (64x64)EPE: 3.30 -> 1.40Improved
use proposed method instead of alternating baseline at 8x8 labelsoptical flow MRF optimization · MPI Sintel sleeping 1 (8x8)EPE: 1.12 -> 0.60Improved
grow label set from 8x8 to 64x64 for proposed methodProposed · MPI SintelEPE: 0.60 -> 1.40Hurt
add label refinement with local alpha-beta swap on 3x3 label neighborhoods (ablation)Proposed · MPI SintelEPE and runtimeMixed

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