Semi-Supervised Object Detection (SSOD), aiming to explore unlabeled data for boosting object detectors, has become an active task in recent years. However, existing SSOD approaches …

2023年4月10日 · This paper proposes a novel Semi-supervised Oriented Object Detection model, termed SOOD, built upon the mainstream pseudo-labeling framework. Towards oriented …

Oriented Object Detection model, termed SOOD, built upon the mainstream pseudo-labeling framework. Towards ori-ented objects in aerial scenes, we design two loss func-tions to …

Experiments on DOTA-v1.5 and DOTA-v1.0 benchmarks demonstrate that the MCL can achieve state-of-the-art performance in the semi-supervised oriented object detection. MMRotate-0.3.4 …

2023年5月25日 · 本文提出了一种新的半监督定向物体检测模型SOOD，该模型基于伪标签框架，并设计了旋转感知自适应加权损失和全局一致性损失，以适应空中场景中多方向物体的检测 …

2024年9月2日 · To address these gaps, we introduce SOOD-ImageNet, a novel dataset comprising around 1.6M images across 56 classes, designed for common computer vision …

Sonu Sood (born 30 July 1973) [2][3] is an Indian actor, film producer, model, humanitarian, and philanthropist who works predominantly in Hindi, Telugu and Tamil films. He is known for his …

2024年7月29日 · 本文提出了一个新颖的半监督定向物体检测模型，称为sood，建立在主流的伪标签框架之上。针对空中场景中的定向物体，我们设计了两个损失函数来提供更好的监督。

2023年10月7日 · 本文提出了一个新颖的半监督定向物体检测模型，称为SOOD，建立在主流的伪标签框架之上。 针对空中场景中的定向物体，我们设计了两个损失函数来提供更好的监督。 …

A Sood, J Cho, KD Hobart, TI Feygelson, BB Pate, M Asheghi, DG Cahill, ... Journal of Applied Physics 119 (17), 175103, 2016. 128: 2016: Direct visualization of thermal conductivity …