AI Paper Atlas

Research map / Detection and segmentation / CNN features

Simultaneous Edge Alignment and Learning

Zhiding Yu, Weiyang Liu, Yang Zou, Chen Feng, Srikumar Ramalingam, B. V. K. Vijaya Kumar, Jan Kautz

ECCV 2018 · Detection and segmentation › CNN features · approach: Box regression and loss design · 94 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 CASENet-S training labels with SEAL jointly aligned labelsCASENet-S · SBD test original labels (Thin)mean MF (%): 73.8 -> 73.8No clear effect
replace CASENet-S training labels with SEAL jointly aligned labelsCASENet-S · SBD test original labels (Raw)mean MF (%): 66.5 -> 70.3Improved
replace CASENet-S with SEALCASENet-S · SBD re-annotated test (Thin)mean MF (%): 65.9 -> 67.0Improved
replace CASENet-S with SEALCASENet-S · SBD re-annotated test (Raw)mean MF (%): 60.3 -> 64.4Improved
refine labels with dense-CRF before training (CASENet-C)CASENet-S · SBD re-annotated test (Thin)mean MF (%): 65.9 -> 64.8Hurt
replace CASENet-S with SEALCASENet-S · Cityscapes val (Raw)mean MF (%): 63.3 -> 65.5Improved
replace CASENet-S with SEALCASENet-S · Cityscapes val (Thin)mean MF (%): 69.1 -> 69.1No clear effect
replace prior state of the art with SEAL under prior benchmarkprevious SOTA · SBD test, prior protocolmean MF (%): 71.4 -> 74.4Improved
add Markov smoothness prior (lambda 0 -> 0.02) to alignment (ablation)SEAL sigma 1,4 · SBD val 0.02 tolerance (Thin)mean MF (%): 72.7 -> 73.4Improved
add Markov smoothness prior (lambda 0 -> 0.02) to alignment (ablation)SEAL sigma 1,4 · SBD val 0.02 tolerance (Raw)mean MF (%): 72.9 -> 70.0Hurt
add biased Gaussian kernel (sigma_x 4 -> 1) (ablation)SEAL lambda 0 · SBD val 0.02 tolerance (Thin)mean MF (%): 71.6 -> 72.7Improved
decrease sigma_y from 4 to 2 (ablation)SEAL lambda 0.02 · SBD val 0.02 tolerance (Raw)mean MF (%): 70.0 -> 68.4Hurt

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