AI Paper Atlas

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

FickleNet: Weakly and Semi-Supervised Semantic Image Segmentation Using Stochastic Inference

Jungbeom Lee, Eunji Kim, Sungmin Lee, Jangho Lee, Sungroh Yoon

CVPR 2019 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 493 citations (OpenAlex)

Check 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 FickleNet localization maps instead of DSRG mapsWeakly supervised segmentation with DeepLab-VGG16 · PASCAL VOC 2012 valmIoU: 59.0 -> 61.2Improved
Use FickleNet localization maps instead of DSRG mapsWeakly supervised segmentation with DeepLab-VGG16 · PASCAL VOC 2012 testmIoU: 60.4 -> 61.9Improved
Use FickleNet localization maps instead of DSRG mapsWeakly supervised segmentation with DeepLab-v2-ResNet101 · PASCAL VOC 2012 valmIoU: 61.4 -> 64.9Improved
Use FickleNet localization maps instead of DSRG mapsWeakly supervised segmentation with DeepLab-v2-ResNet101 · PASCAL VOC 2012 testmIoU: 63.2 -> 65.3Improved
Use FickleNet with 1.4K strong and 9K weak training data instead of DSRGSemi-supervised segmentation · PASCAL VOC 2012 valmIoU: 64.3 -> 65.8Improved
Add map expansion to the naive implementation (ablation)FickleNet training · Training iterationstime per iteration: 20 sec/iter -> 1.3 sec/iterImproved
Add map expansion to the naive implementation (ablation)FickleNet localization-map extraction · CAM extractiontime per image: 2.98 sec/img -> 0.21 sec/imgImproved
Use stochastic selection in both training and inference instead of general dropout in both (ablation)FickleNet · PASCAL VOC 2012 valmIoU: 49.1 -> 61.2Improved
Use stochastic selection during inference rather than deterministic inference after stochastic training (ablation)FickleNet · PASCAL VOC 2012 valmIoU: 59.6 -> 61.2Improved
Use stochastic selection during training rather than deterministic training with deterministic inference (ablation)FickleNet · PASCAL VOC 2012 valmIoU: 59.0 -> 61.2Improved
Increase FickleNet dropout rate from 0.3 to 0.9 (ablation)FickleNet · PASCAL VOC 2012 valmIoU: 58.8 -> 61.2Improved
Replace location-wise hidden-unit selection with general dropout at rate 0.9 (ablation)FickleNet localization and segmentation · PASCAL VOC 2012 valmIoU: 61.2 -> 49.1Hurt

Later papers that compared with this method

10 later accepted papers report FickleNet as a baseline in their results tables; 9 of them report a better number on most of the results they share with it.

2 more not listed.

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