Tahira Shehzadi — accepted AI-conference papers

2025

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 2025poster

This paper addresses key limitations in current Semi-Supervised Object Detection (SSOD) frameworks, focusing on issues related to pseudo-label quality, confidence bias, and inefficient query generation. Traditional methods, including CNN-based and DETR-based architectures, often face challenges such…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

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

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

CVPR 2024poster

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 a…

Cited by 24 Source ↗PDF ↗Scholar ↗