AI Paper Atlas

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

STEP-DETR: Advancing DETR-based Semi-Supervised Object Detection with Super Teacher and Pseudo-Label Guided Text Queries

Tahira Shehzadi, Khurram Azeem Hashmi, Shalini Sarode, Didier Stricker, Muhammad Zeshan Afzal

ICCV 2025 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection · 6 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 Pseudo-Label Text Queries (ablation)Semi-DETR · COCO 10% labeledmAP: 43.5 -> 44.7Improved
add Denoising Text Guided Object Queries (ablation)Semi-DETR + text queries · COCO 10% labeledmAP: 44.7 -> 45.1Improved
add Query Refinement (ablation)Semi-DETR + text and denoising queries · COCO 10% labeledmAP: 45.1 -> 45.4Improved
use text queries instead of sparse visual queries (ablation)STEP-DETR · COCO 10% labeledmAP: 44.3 -> 45.4Improved
use consistency queries instead of standard queries (ablation)DINO teacher-student SSOD · COCO 10% labeledmAP: 41.3 -> 43.5Improved
add Super Teacher (ablation)DINO · COCO 10% labeledmAP: 35.0 -> 45.4Improved
add NMS on top of Super Teacher (ablation)STEP-DETR · COCO 10% labeledmAP: 45.4 -> 45.7No clear effect
use text guided denoising instead of standard denoising (ablation)Semi-DETR · COCO 10% labeledmAP: 43.5 -> 43.8Improved
use query similarity refinement instead of simple concat (ablation)STEP-DETR · COCO 10% labeledmAP: 45.1 -> 45.4Improved
add Query Refinement to reduce redundant queriesSTEP-DETR · COCO one-to-many trainingtraining time per 1k iterations: 38.56 -> 30.98Improved
STEP-DETR versus Semi-DETR with 10% labelsSTEP-DETR · COCO-Partial 10% labeledmAP: 43.5 -> 45.4Improved
STEP-DETR versus Semi-DETR on full COCO plus unlabeledSTEP-DETR · COCO-FullmAP: 50.4 -> 52.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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