56 datasets found

The ApolloScape dataset is a large-scale dataset for autonomous driving, containing images and annotations.

The dataset used for the experiments in the paper, which includes ImageNet, MS COCO, Cityscapes, and ADE20K datasets.

A dataset for object detection tasks, including deformable transformers.

Dense computer vision tasks such as object detection and segmentation require effective multi-scale feature representation for detecting or classifying objects or regions with...

Few-shot segmentation remains challenging due to the limitations of its labeling information for unseen classes. Most previous approaches rely on extracting high-level feature...

A dataset for image classification, object detection, and visual relationship detection.

Open-vocabulary object detection (OvOD) has transformed detection into a language-guided task, empowering users to freely define their class vocabularies of interest during...

ImageNet classification dataset, COCO dataset

The inaturalist species classification and detection dataset.

The dataset used for the experiments of the paper.

The UniPerf dataset is a benchmark for perceptual parsing for scene understanding.

A dataset of videos of a robot interacting with blocks of different shapes and colors placed on a table in a simulation environment.

The Sim10k dataset is a synthetic dataset for object detection.

The VOC2012 dataset is a multi-label image recognition dataset. It contains 11,540 train-val images and 10,991 test images.

Alpha-CLIP is an enhanced version of CLIP with an auxiliary alpha channel to suggest attentive regions and fine-tuned with constructed millions of RGBA region-text pairs.

Two novel datasets are created using the ARS pipeline, one on electromechanical components (industrial scenario) and one on fruits (daily-living scenario).

iCubWorld Transformations (iCWT): a dataset for object recognition and manipulation

Open-set object detection datasets

Open-set object detection datasets

The Places dataset is a large-scale dataset for scene recognition, containing 1 million images from 365 categories.