-
YOLOF dataset
The dataset used in the paper is YOLOF dataset. -
ImageNet, MS COCO, and Pascal VOC datasets
The dataset used in the paper is ImageNet, MS COCO, and Pascal VOC datasets. -
Broad Bioimage Benchmark Collection (BBBC)
The proposed model uses the Broad Bioimage Benchmark Collection (BBBC) dataset to detect objects in images. -
Argoverse-HD
The dataset used in the paper is Argoverse-HD. -
Argoverse-HD, Cityscapes, and nuScenes
The dataset used in the paper is Argoverse-HD, Cityscapes, and nuScenes. -
MSCOCO dataset
The MSCOCO dataset is a large-scale image captioning dataset, containing 113,287 images with 5,000 validation images and 5,000 test images. The dataset is used for training and... -
ICCV dataset
The ICCV dataset is a benchmark for learning deep object detectors from 3D models. -
Pets 2016 dataset
The Pets 2016 dataset is a benchmark for object detection in images. -
SafeSea dataset
The SafeSea dataset is created using the SafeSea method, involving the transformation of 300 calm ocean background images originally sourced from the 'SeaDroneSee' dataset. -
WRGB-D Scenes Dataset
A large-scale hierarchical multi-view RGB-D object dataset. -
BigBird Dataset
A large-scale 3D database of object instances for scene understanding. -
Kitchen Scenes Dataset
A new multi-view RGB-D dataset for object instance detection and recognition of commonly encountered household objects in realistic settings. -
Occluded Prohibited Items X-ray (OPIXray) image benchmark
The Occluded Prohibited Items X-ray (OPIXray) image benchmark is a high-quality object detection dataset for security inspection, containing 8885 X-ray images of 5 categories of... -
KITTI object detection benchmark dataset
The KITTI object detection benchmark dataset. -
ProgS-RCNN
ProgS-RCNN: Progressive End-to-End Object Detection in Crowded Scenes -
CrowdHuman
CrowdHuman is a challenging benchmark to evaluate the ability of crowded scene detection of detectors, which contains about 15k training images and 4k images for evaluation. -
COCO test-dev
The COCO test-dev dataset is used for instance segmentation. It contains 20k test-dev images.
