345 datasets found

The Faster R-CNN dataset is a large-scale object detection dataset, containing over 100,000 images with 80 categories.

The PASCAL Context dataset is a benchmark for multi-task learning in computer vision. It contains 10103 images with 5 tasks: semantic segmentation, human body part segmentation,...

The COCO 2017 object detection dataset is used in this paper for evaluation of the proposed DEYOv2 model.

Data augmentation has been an indispensable tool to improve the performance of deep neural networks, however the augmentation can hardly transfer among different tasks and...

The dataset used in this paper is a simulated dataset with 200 variables and 50 observations. The variables are generated from a multivariate normal distribution with a...

The dataset used in this paper for testing the 3D-RecGAN++ model. It contains 1.5k SV and 2.5k CV testing datasets for each of the 6 categories.

A dataset for segment anything model (SAM) to evaluate its performance.

LVIS: A dataset for large vocabulary instance segmentation.

Segment anything model (SAM) addresses two practical yet challenging segmentation tasks: segment anything (SegAny), which utilizes a certain point to predict the mask for a...

The authors' own dataset is used for object detection in thermal images.

A fine-grained vehicle detection dataset with 3,640 instances and 1,210 images, which provides fine-grained information of car categories.

DOTA dataset is a large-scale dataset for object detection in aerial images including 2806 aerial images with each image ranging from 800 × 800 to 4000 × 4000 pixels collected...

Video object segmentation is a fundamental task in many important areas such as autonomous driving, robotic manipulation, video surveillance, and video editing.

The VIPSeg dataset contains videos with annotations for video panoptic segmentation.

The LVIS-92i dataset contains 92 images with 92 object categories.

The PACO-Part dataset contains 59 images with 59 object categories.

The PerSeg dataset contains 40 images with 40 object categories.

The Caltech-UCSD-Birds-200-2011 dataset contains images of 200 bird species.

The dataset used for pothole detection using deep learning

A dataset of images with pothole annotations from various sources, including Google Earth Pro, AUTOPILOT videos, and GoPro camera images.