Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection

Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 5840-5850

Abstract


In this paper we address the limitations of the DETR-based semi-supervised object detection (SSOD) framework particularly focusing on the challenges posed by the quality of object queries. In DETR-based SSOD the one-to-one assignment strategy provides inaccurate pseudo-labels while the one-to-many assignments strategy leads to overlapping predictions. These issues compromise training efficiency and degrade model performance especially in detecting small or occluded objects. We introduce Sparse Semi-DETR a novel transformer-based end-to-end semi-supervised object detection solution to overcome these challenges. Sparse Semi-DETR incorporates a Query Refinement Module to enhance the quality of object queries significantly improving detection capabilities for small and partially obscured objects. Additionally we integrate a Reliable Pseudo-Label Filtering Module that selectively filters high-quality pseudo-labels thereby enhancing detection accuracy and consistency. On the MS-COCO and Pascal VOC object detection benchmarks Sparse Semi-DETR achieves a significant improvement over current state-of-the-art methods that highlight Sparse Semi-DETR's effectiveness in semi-supervised object detection particularly in challenging scenarios involving small or partially obscured objects.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Shehzadi_2024_CVPR, author = {Shehzadi, Tahira and Hashmi, Khurram Azeem and Stricker, Didier and Afzal, Muhammad Zeshan}, title = {Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5840-5850} }