AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition

Jiebin Yan, Yu Zhong, Yuming Fang, Zhangyang Wang, Kede Ma

IJCV 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 22 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 category constraint to MAD selection (ablation)MAD image selection · PASCAL VOC MAD setimage diversityImproved
add scale constraint on top of category constraint (ablation)MAD image selection · PASCAL VOC MAD setimage diversityImproved
switch concordance measure from mIoU to FWIoU (ablation)MAD ranking · PASCAL VOCSRCC of aggressiveness ranking: 0.891No clear effect
switch concordance measure from mIoU to MPA (ablation)MAD ranking · PASCAL VOCSRCC of aggressiveness ranking: 0.878No clear effect
switch concordance measure from mIoU to MPA (ablation)MAD ranking · PASCAL VOCSRCC of resistance ranking: 0.830No clear effect
evaluate on MAD set instead of PASCAL VOC testten segmentation models · PASCAL VOCmIoU: all above 0.6 -> 84.7% below 0.6Hurt
detection auxiliary task (BlitzNet) vs attention modules (EMANet, PSANet)segmentation models · PASCAL VOC MADaggressiveness rank: BlitzNet mIoU rank 7 -> A rank 3; EMANet 2 -> 5Mixed
multi-resolution fusion and chained residual pooling (RefineNet)segmentation model · PASCAL VOC MADaggressiveness rank: mIoU rank 6 -> A rank 2Improved
more training data (Cityscapes coarse + Mapillary) for HANetHANet · WildDash MADrank: A rank 1, R rank 1Improved
graph convolution modules in DGCNetDGCNet · WildDash MADrank: mIoU rank 2 -> A rank 4Hurt

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