AI Paper Atlas

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

Weakly Supervised Learning of Semantic Correspondence through Cascaded Online Correspondence Refinement

Yiwen Huang, Yixuan Sun, Chenghang Lai, Qing Xu, Xiaomei Wang, Xuli Shen, Weifeng Ge

ICCV 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 4 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
pretrain matching models on SC-ImageNet pseudo-labels, then fine-tuneVAT · SPair-71kPCK@0.10: 55.5 -> 60.3Improved
pretrain on SC-ImageNet then fine-tuneCATs · SPair-71kPCK@0.10: 49.9 -> 54.6Improved
pretrain on SC-ImageNet then fine-tuneSCorrSAN · SPair-71kPCK@0.10: 55.3 -> 58.9Improved
pretrain on SC-ImageNet then fine-tuneTransforMatcher · PF-WILLOWPCK@0.05 / PCK@0.10: 48.9 -> 49.9 at 0.05; 76.0 -> 77.2 at 0.10Mixed
pretrain on SC-ImageNet then fine-tuneDHPF · PF-PASCALPCK@0.10: 90.7 -> 90.7No clear effect
add saliency detection to pseudo-label generator (ablation)pseudo-label generator · PF-PASCALPCK@0.05: 55.9 -> 56.8Improved
add regularized Hough matching (RHM) (ablation)pseudo-label generator · PF-PASCALPCK@0.05: 55.6 -> 56.8Improved
use independent (non-shared) gated cross-attention in each stage (ablation)pseudo-label generator · PF-PASCALPCK@0.05: 52.6 -> 56.8Improved
include the region-level stage (ablation)pseudo-label generator · PF-PASCALPCK@0.05: 51.0 -> 56.1Improved
include the pixel-level stage (ablation)pseudo-label generator · PF-PASCALPCK@0.05: 56.1 -> 56.8Improved
raise input resolution from 256 to 512 (ablation)pseudo-label generator · PF-PASCALPCK@0.05: 53.2 -> 56.8Improved
use RHM hyperpixel length 5 instead of 3 or 7 (ablation)pseudo-label generator · PF-PASCALPCK@0.05: 56.0 (3) / 56.8 (5) / 56.2 (7)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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