AI Paper Atlas

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

Box2Seg: Attention Weighted Loss and Discriminative Feature Learning for Weakly Supervised Segmentation

Viveka Kulharia, Siddhartha Chandra, Amit Agrawal, Philip Torr, Ambrish Tyagi

ECCV 2020 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 101 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 GrabCut pseudo-labels instead of box masks only (ablation)segmentation network · PASCAL VOC 2012 valmIoU: 59.3 -> 72.7Improved
add affinity (pixel embedding) loss (ablation)GrabCut baseline · PASCAL VOC 2012 valmIoU: 72.7 -> 73.9Improved
add attention weighted loss with box regularization (ablation)GrabCut baseline · PASCAL VOC 2012 valmIoU: 72.7 -> 74.1Improved
add attention weighted loss with fill-rate regularization (ablation)GrabCut baseline · PASCAL VOC 2012 valmIoU: 72.7 -> 74.6Improved
use fill-rate regularization instead of box regularization of attention map (ablation)attention weighted loss · PASCAL VOC 2012 valmIoU: 74.1 -> 74.6Improved
add affinity loss on top of attention weighted loss (ablation)AW-fr · PASCAL VOC 2012 valmIoU: 74.6 -> 74.9Improved
add attention weighted loss in fully supervised training (ablation)supervised baseline · PASCAL VOC 2012 val (fully supervised)mIoU: 73.6 -> 75.1Improved
add dense CRF post-processing (ablation)Box2Seg · PASCAL VOC 2012 valmIoU: 74.9 -> 76.4Improved
fine-tune with 5% pixel-level labelsBox2Seg · PASCAL VOC 2012 val (semi-supervised)mIoU: 74.9 -> 78.7Improved
fine-tune with 10% pixel-level labelsBox2Seg · PASCAL VOC 2012 val (semi-supervised)mIoU: 74.9 -> 83.1Improved
fine-tune with 100% pixel-level labelsBox2Seg · PASCAL VOC 2012 val (semi-supervised)mIoU: 74.9 -> 86.4Improved
use Box2Seg weak model as initialization instead of ImageNetfully supervised DeepLab · PASCAL VOC 2012 val (semi-supervised)mIoU: 74.5 -> 86.4Improved

Later papers that compared with this method

3 later accepted papers report Box2Seg as a baseline in their results tables; 1 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