目标检测数据集的分析

Analysis on Object Detection Datasets.

Detecting Twenty-thousand Classes using Image-level Supervision

使用图像级监督检测两万个类别.

Open Vocabulary Object Detection with Pseudo Bounding-Box Labels

通过伪边界框标签实现开放词汇目标检测.

Open-vocabulary Object Detection via Vision and Language Knowledge Distillation

通过视觉和语言知识蒸馏实现开放词汇目标检测.

Open-Vocabulary Object Detection Using Captions

使用描述进行开集目标检测.

MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding

MDETR：用于端到端多模态理解的调制检测.