AI Paper Atlas

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

Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling

Lixiang Ru, Bo Du, Yibing Zhan, Chen Wu

IJCV 2022 · Detection and segmentation › Weakly supervised detection and segmentation · approach: CAM refinement and prototypes · 66 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 hybrid pooling (ablation)ResNet101 baseline · PASCAL VOC trainCAM mIoU: 49.5 -> 54.0Improved
add visual words learning (memory-bank) on top of HP (ablation)HP ResNet101 · PASCAL VOC trainCAM mIoU: 54.0 -> 56.9Improved
add visual words learning (learning-based, with DeCov) on top of HP (ablation)HP ResNet101 · PASCAL VOC trainCAM mIoU: 54.0 -> 57.3Improved
add DeCov regularization to the learning-based codebook (ablation)VWL-L · PASCAL VOC trainCAM mIoU: 55.1 -> 57.3Improved
use random sample codebook initialization instead of random (ablation)VWL-L · PASCAL VOC trainCAM mIoU: 57.3 -> 55.8Hurt
use random sample codebook initialization instead of random (ablation)VWL-M · PASCAL VOC trainCAM mIoU: 56.9 -> 56.6No clear effect
add GAP into hybrid pooling (ablation)HP · PASCAL VOC trainCAM mIoU: about 16% mIoU improvementImproved
use multi-scale split sizes {1,2,4} instead of {1} (ablation)HP · PASCAL VOC trainCAM mIoU: 56.2 -> 57.3Improved
add split size 8 to {1,2,4} (ablation)HP · PASCAL VOC trainCAM mIoU: 57.3 -> 57.0No clear effect
replace GAP with hybrid pooling (ablation)ResNet101 baseline · PASCAL VOC trainCAM mIoU: 49.5 -> 54.0Improved
use GAP rather than HP to predict visual words (ablation)VWL · PASCAL VOC trainCAM mIoU: 55.5 -> 57.3Improved
memory-bank vs learning-based strategy for visual word quality (ablation)VWL · PASCAL VOC train classification accuracyclassification accuracy (%): 81.3 -> 84.8Improved

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