Object Detector
Object detection, aiming to identify and locate objects within images or videos, is a core computer vision task with applications ranging from autonomous driving to medical image analysis. Current research emphasizes improving accuracy, particularly in addressing false positives and handling challenging conditions like occlusions, varying viewpoints, and noisy data, often employing transformer-based architectures and leveraging techniques like knowledge distillation and semi-supervised learning. These advancements are crucial for enhancing the reliability and robustness of object detectors in real-world applications, impacting fields requiring accurate and efficient scene understanding.
Papers
Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection
Fatih Cagatay Akyon, Sinan Onur Altinuc, Alptekin Temizel
An experimental study of the vision-bottleneck in VQA
Pierre Marza, Corentin Kervadec, Grigory Antipov, Moez Baccouche, Christian Wolf
Single-stage Rotate Object Detector via Two Points with Solar Corona Heatmap
Beihang Song, Jing Li, Shan Xue, Jun Chang, Jia Wu, Jun Wan, Tianpeng Liu
Detecting Twenty-thousand Classes using Image-level Supervision
Xingyi Zhou, Rohit Girdhar, Armand Joulin, Philipp Krähenbühl, Ishan Misra
A Novel Incremental Learning Driven Instance Segmentation Framework to Recognize Highly Cluttered Instances of the Contraband Items
Taimur Hassan, Samet Akcay, Mohammed Bennamoun, Salman Khan, Naoufel Werghi