AI Paper Atlas

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

MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation

Lian Xu, Mohammed Bennamoun, Farid Boussaïd, Hamid Laga, Wanli Ouyang, Dan Xu

TPAMI 2024 · Detection and segmentation › Weakly supervised detection and segmentation · approach: CAM refinement and prototypes · 95 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
use multiple class tokens (MCTformer attention) instead of a single class token with CAM (TS-CAM*) (ablation)MCTformer · PASCAL VOC train (seed)mIoU: 41.3 -> 47.2Improved
add PatchAffinity refinement to attention maps (ablation)MCTformer (Attention) · PASCAL VOC train (seed)mIoU: 47.2 -> 55.2Improved
add PatchCAM fusion to attention maps (ablation)MCTformer (Attention) · PASCAL VOC train (seed)mIoU: 47.2 -> 58.2Improved
add PatchAffinity refinement to the fused PatchCAM and attention maps (ablation)MCTformer (Attention + PatchCAM) · PASCAL VOC train (seed)mIoU: 58.2 -> 61.7Improved
add PatchAffinity to maps for training the segmentation network (ablation)MCTformer · PASCAL VOC val (segmentation)mIoU: 55.6 -> 58.8; 61.1 -> 62.6Improved
average pooling of class tokens instead of a fully-connected layer for class prediction (ablation)MCTformer · PASCAL VOC train (seed)mIoU: 41.5 -> 47.2Improved
average pooling of class tokens instead of max pooling (ablation)MCTformer · PASCAL VOC train (seed)mIoU: 26.8 -> 47.2Improved
use GWRP instead of GAP in CAM module (ablation)MCTformer+ · PASCAL VOC train (seed)mIoU: 66.1 -> 68.8Improved
use GWRP instead of GMP in CAM module (ablation)MCTformer+ · PASCAL VOC train (seed)mIoU: 59.4 -> 68.8Improved
add CCT module on top of GAP (224x224 and 448x448 training) (ablation)MCTformer+ · PASCAL VOC train (seed)mIoU: 63.2 -> 64.5 (224); 63.6 -> 66.1 (448)Improved
add CCT module on top of GWRP (224x224 and 448x448 training) (ablation)MCTformer+ · PASCAL VOC train (seed)mIoU: 64.8 -> 65.8 (224); 65.9 -> 68.8 (448)Improved
apply CCT only on last layer instead of no CCT (ablation)MCTformer+ · PASCAL VOC train (seed)mIoU: 64.8Hurt

Later papers that compared with this method

6 later accepted papers report MCTformer+ as a baseline in their results tables; 6 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