482 datasets found

The dataset used in the paper is the MS-COCO 2017 detection dataset.

Region-based Fully Convolutional Networks for object detection

The proposed end-to-end pseudo-label based semi-supervised object detection framework, which simultaneously performs pseudo-labeling for unlabelled images and trains a detector...

The VisDrone2019 dataset contains 10,209 high-resolution images with ten categories: pedestrian, people, bicycle, car, van, truck, tricycle, awning-tricycle, bus, and motor.

Detecting objects from aerial images poses significant challenges due to the following factors: 1) Aerial images typically have very large sizes, generally with millions or even...

The dataset used in the paper is the VOC dataset, which is a dataset for object detection and segmentation.

The CARPK dataset is a large-scale aerial dataset for counting cars in parking lots. It contains images with a top-down view covering 4 different parking lots.

The Foggy Cityscapes dataset is an extension to the Cityscapes dataset, containing 5k diverse real-world urban driving scenes with fog.

ImageNet classification dataset, COCO dataset

YOLOv4 dataset contains object detection tasks.

Object detection in 20 years: A survey dataset contains object detection tasks.

The proposed method of automatic dataset generation for cards detection and classification makes it possible to obtain any number of images of any size, which can be used to...

The dataset used in the paper for attention-oriented data analysis and attention-based adversarial defense.

The ACFR Apple dataset is used for object detection tasks.

The proposed MG-ViT model is used for few-shot learning on the Agri-ImageNet and ACFR apple detection tasks.

Fast R-CNN is a clean and fast update to R-CNN and SPPnet. It uses a single-stage training algorithm that jointly learns to classify object proposals and refine their spatial...

CornerNet detects objects as a pair of keypoints— the top-left corner and bottom-right corner of the bounding box.

This dataset contains images of cats and dogs, which is used for training deep neural networks.

The inaturalist species classification and detection dataset.

The Behave dataset contains various scenes with human-object interactions, and is used to evaluate the proposed object-level 3D semantic mapping approach.