AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

Learning Semantic Correspondence with Sparse Annotations

Shuaiyi Huang, Luyu Yang, Bo He, Songyang Zhang, Xuming He, Abhinav Shrivastava

ECCV 2022 · Label-efficient and robust learning › Noisy labels · approach: Instance-dependent noise modeling · 29 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 Efficient-SCE spatial context encoder (ablation)base network · SPair-71kPCK: 14.7 -> 33.4Improved
add high-resolution loss (ablation)network with Efficient-SCE · SPair-71kPCK: 33.4 -> 40.6Improved
finetune the backbone (ablation)network with Efficient-SCE and HRLoss · SPair-71kPCK: 40.6 -> 49.8Improved
add teacher-student learning without denoising (ablation)base network · SPair-71kPCK: 49.8 -> 49.7No clear effect
add dynamic label selection (ablation)teacher-student model · SPair-71kPCK: 49.7 -> 51.5Improved
add label mask dilation (ablation)teacher-student with dynamic selection · SPair-71kPCK: 51.5 -> 55.3Improved
use single offline teacher (ablation)base network · SPair-71kPCK: 49.8 -> 52.4Improved
use mutual online teachers instead of single offline teacher (ablation)teacher-student · SPair-71kPCK: 52.4 -> 55.3Improved
use dilation kernel size 7 instead of 3 (ablation)label mask dilation · SPair-71kPCK: 54.0 -> 55.3Improved
use dilation kernel size 15 instead of 7 (ablation)label mask dilation · SPair-71kPCK: 55.3 -> 52.0Hurt
use ours (MT) instead of CATsPCK on SPair-71k · SPair-71kPCK: 49.9 -> 55.3Improved
use ours (MT) instead of CATs at alpha 0.15PF-WILLOW · PF-WILLOWPCK@0.15: 90.3 -> 89.8Hurt

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