AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

SegSort: Segmentation by Discriminative Sorting of Segments

Jyh-Jing Hwang, Stella X. Yu, Jianbo Shi, Maxwell D. Collins, Tien-Ju Yang, Xiao Zhang, Liang-Chieh Chen

ICCV 2019 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 129 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 pixel-wise softmax with SegSort metric learningDeepLabv3+ / MNV2 · PASCAL VOC 2012 valmIoU: 72.51 -> 74.94Improved
replace pixel-wise softmax with SegSort metric learningPSPNet / ResNet-101 · PASCAL VOC 2012 valmIoU: 80.12 -> 81.77Improved
replace pixel-wise softmax with SegSort metric learningDeepLabv3+ / MNV2 · PASCAL VOC 2012 valboundary f-measure: 50.90 -> 58.83Improved
replace pixel-wise softmax with SegSortDeepLabv3+ / ResNet-101 · PASCAL VOC 2012 valmIoU: 78.24 -> 78.85Improved
replace pixel-wise softmax with SegSortPSPNet / ResNet-101 · Cityscapes valmIoU: 76.72 -> 78.15Improved
replace ASM with SegSortPSPNet / ResNet-101 · PASCAL VOC 2012 valmIoU: 81.43 -> 81.77Improved
train unsupervised SegSort instead of clustering pretrained features (ablation)HED-owt-ucm baseline · PASCAL VOC 2012 valmIoU: 49.50 -> 55.86Improved
add unsupervised pretraining before supervised training on train (ablation)SegSort · PASCAL VOC 2012 valmIoU: 71.86 -> 72.47Improved
add unsupervised pretraining before supervised training on train (ablation)SegSort · PASCAL VOC 2012 valboundary f-measure: 55.70 -> 56.52Improved
increase k-means iterations from 4 to 10 at inference (ablation)SegSort (11-NN) · Cityscapes valmIoU: 78.50 -> 78.69Improved
increase nearest neighbors from 1 to 11 at inference (ablation)SegSort (4 iter) · Cityscapes valmIoU: 78.05 -> 78.50Improved
vary the number of nearest neighbors from 1 to 31 (ablation)SegSort PSPNet · PASCAL VOC 2012 valmIoU: 0.4%No clear effect

Later papers that compared with this method

2 later accepted papers report SegSort as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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