265 datasets found

The COCO 2017 detection benchmark dataset is used for evaluating the proposed TSP-FCOS and TSP-RCNN models.

Object detection in aerial images has greater rotational and scale variations because of the overhead image capture, which requires the detection model to more flexibly handle...

The SBD dataset is a benchmark dataset for semantic segmentation and object detection.

The COCO 2017 Dataset is a large-scale benchmark dataset for object detection, semantic segmentation, and instance segmentation.

YOLOv7 surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 160 FPS and has the highest accuracy 56.8% AP test-dev / 56.8% AP min-val among...

Knowledge distillation learns a lightweight student model that mimics a cumbersome teacher. Existing methods regard the knowledge as the feature of each instance or their...

The Track Anything Rapter (TAR) project utilizes state-of-the-art pre-trained models to accurately detect and track target objects through multimodal queries.

The MS COCO 2014 Dataset contains images of 91 object categories, which contains 82783 training images, 40504 validation images and 40775 testing images.

The MS COCO detection dataset is a large-scale object detection benchmark.

Object detection is one of the most widely studied tasks in computer vision with many applications to tasks such as object tracking, instance segmentation, and image captioning.

The dataset used in the paper is the MSCOCO validation set.

A dataset for semantic object classes in video.

The WoodScape dataset consists of 10,000 annotated images captured from four different view angles: Front View (FV), Mirror-View Right (MVR), Mirror-View Left (MVL), and Rear...

Panoptic segmentation aims to unify instance and semantic segmentation in the same framework. Existing works propose to merge instance and semantic segmentation using...

Panoptic segmentation aims to unify instance and semantic segmentation in the same framework. Existing works propose to merge instance and semantic segmentation using...

The Stanford Cars dataset is a dataset of images of cars, with 196 categories and approximately 16,000 images. The authors created a synthetic dataset by adding occlusions of...

A dataset of hexagonal contact hole DSA patterns with defects, labeled by multiple human labelers.

The DAVIS-2017 dataset is a benchmark for video object segmentation

Object detection has gained great progress driven by the development of deep learning. Compared with a widely studied task – classification, generally speaking, object detection...

Road damage data collected from Google Street View for training deep learning models.