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

Source: [Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection](<https://www.sota2.com/research/paper/68fa72b91e209131cea5825d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-14T19:25:31.055Z

Authors: Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal

Published: 2024-04-02T10:22:23.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2404.01819>)

[PDF](<https://arxiv.org/pdf/2404.01819.pdf>)