# DExTeR: Weakly Semi-Supervised Object Detection with Class and Instance Experts for Medical Imaging

arXiv: https://arxiv.org/abs/2601.13954 · HTML: https://mlsanity.com/paper/2601.13954/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 35 references that are in the map.
- First posted on arXiv 20 Jan 2026.

## Builds on (most cited first, 21 of 21)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [DN-DETR: Accelerate DETR Training by Introducing Query DeNoising](https://mlsanity.com/paper/2203.01305/) (2022)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [What's the Point: Semantic Segmentation with Point Supervision](https://mlsanity.com/paper/1506.02106/) (2015)
- [VinDr-CXR: An open dataset of chest X-rays with radiologist's annotations](https://mlsanity.com/paper/2012.15029/) (2020)
- [A Review of Sparse Expert Models in Deep Learning](https://mlsanity.com/paper/2209.01667/) (2022)
- [PCL: Proposal Cluster Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1807.03342/) (2018)
- [Points as Queries: Weakly Semi-supervised Object Detection by Points](https://mlsanity.com/paper/2104.07434/) (2021)
- [Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection](https://mlsanity.com/paper/2103.16368/) (2021)
- [Latent Graph Representations for Critical View of Safety Assessment](https://mlsanity.com/paper/2212.04155/) (2022)
- [Data-Centric Foundation Models in Computational Healthcare: A Survey](https://mlsanity.com/paper/2401.02458/) (2024)
- [Weakly-Supervised Learning for Tool Localization in Laparoscopic Videos](https://mlsanity.com/paper/1806.05573/) (2018)
- [MOSaiC: a Web-based Platform for Collaborative Medical Video Assessment and Annotation](https://mlsanity.com/paper/2312.08593/) (2023)
- [Scaling Novel Object Detection with Weakly Supervised Detection Transformers](https://mlsanity.com/paper/2207.05205/) (2022)
- [On-the-Fly Point Annotation for Fast Medical Video Labeling](https://mlsanity.com/paper/2404.14344/) (2024)

## Built on by (most cited first, 1 of 1)

- [Progressive Pseudo-Label Optimization for Point-Supervised Change Detection](https://mlsanity.com/paper/2609.02171/) (2026)

## Abstract (arXiv)

Detecting anatomical landmarks in medical imaging is essential for diagnosis and intervention guidance. However, object detection models rely on costly bounding box annotations, limiting scalability. Weakly Semi-Supervised Object Detection (WSSOD) with point annotations proposes annotating each instance with a single point, minimizing annotation time while preserving localization signals. A Point-to-Box teacher model, trained on a small box-labeled subset, converts these point annotations into pseudo-box labels to train a student detector. Yet, medical imagery presents unique challenges, including overlapping anatomy, variable object sizes, and elusive structures, which hinder accurate bounding box inference. To overcome these challenges, we introduce DExTeR (DETR with Experts), a transformer-based Point-to-Box regressor tailored for medical imaging. Built upon Point-DETR, DExTeR encodes single-point annotations as object queries, refining feature extraction with the proposed class-guided deformable attention, which guides attention sampling using point coordinates and class labels to capture class-specific characteristics. To improve discrimination in complex structures, it introduces CLICK-MoE (CLass, Instance, and Common Knowledge Mixture of Experts), decoupling class and instance representations to reduce confusion among adjacent or overlapping instances. Finally, we implement a multi-point training strategy which promotes prediction consistency across different point placements, improving robustness to annotation variability. DExTeR achieves state-of-the-art performance across three datasets spanning different medical domains (endoscopy, chest X-rays, and endoscopic ultrasound) highlighting its potential to reduce annotation costs while maintaining high detection accuracy.