AI Paper Atlas

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

Seminar Learning for Click-Level Weakly Supervised Semantic Segmentation

Hongjun Chen, Jinbao Wang, Hong Cai Chen, Xiantong Zhen, Feng Zheng, Rongrong Ji, Ling Shao

ICCV 2021 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 35 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 L_CRF to L_pCE (ablation)click-supervised DeepLab-v3+ ResNet101 · Pascal VOC 2012 valmIOU (%): 54.70 -> 55.63No clear effect
add L_CRF to L_pCE (ablation)click-supervised DeepLab-v3+ MobileNet · Pascal VOC 2012 valmIOU (%): 50.85 -> 48.75Hurt
add pixel consistency loss L_pCons (EMA teacher) to L_pCE (ablation)click-supervised DeepLab-v3+ ResNet101 · Pascal VOC 2012 valmIOU (%): 54.70 -> 61.47Improved
add L_pCons to L_pCE + L_CRF (ablation)click-supervised DeepLab-v3+ ResNet101 · Pascal VOC 2012 valmIOU (%): 55.63 -> 70.29, increasing by 14.66%Improved
add L_CRF to L_pCE + L_pCons (ablation)click-supervised DeepLab-v3+ ResNet101 · Pascal VOC 2012 valmIOU (%): 61.47 -> 70.29, exceeds by 8.82%Improved
add L_pCons to L_pCE + L_CRF (ablation)click-supervised DeepLab-v3+ MobileNet · Pascal VOC 2012 valmIOU (%): 48.75 -> 62.03Improved
add heterogeneous pseudo-label loss L_pseudo (student-student module) (ablation)seminar learning ResNet101 · Pascal VOC 2012 valmIOU (%): 70.29 -> 72.51, extra 2.22%Improved
add heterogeneous pseudo-label loss L_pseudo (student-student module) (ablation)seminar learning MobileNet · Pascal VOC 2012 valmIOU (%): 62.03 -> 64.44Improved
generate pseudo-labels from the same network (self-generation) instead of a separate ancillary network (ablation)seminar learning · Pascal VOC 2012 valmIOU (%)Hurt
add a first student-student module (ablation)seminar learning ResNet101 · Pascal VOC 2012 valmIOU (%): 70.29 -> 72.51Improved
add a first student-student module (ablation)seminar learning MobileNet · Pascal VOC 2012 valmIOU (%): 60.59 -> 62.59Improved
chain more than one student-student module (ablation)seminar learning · Pascal VOC 2012 valmIOU (%)No clear effect

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