25 datasets found

Tomatopia is a new, large-scale dataset of greenhouse tomatoes, manually annotated in a pixel-wise manner. The dataset comprises high-resolution RGB-D images and pixel-level...

COCO dataset, ADE20K dataset, PASCAL Context dataset, LVIS dataset

The dataset used for training and testing the proposed LSSC system, which consists of 1530 training images and 170 test images in RGB format.

The MIT-Adobe FiveK dataset, a large-scale dataset for image segmentation and object detection.

The Synthia dataset is a large-scale urban scene understanding dataset, containing 9000 samples. It is used for semantic segmentation tasks.

The dataset used in this paper for occluded apple tree segmentation.

Knee OsteoArthritis (KOA) dataset used for early detection of KOA (KL-0 vs KL-2) using Vision Transformer (ViT) model with selective shuffled position embedding and key-patch...

The NYU-Depth V2 dataset contains pairs of RGB and depth images collected from Microsoft Kinect in 464 indoor scenes.

The MS COCO dataset is a large benchmark for image captioning, containing 328K images with 5 caption descriptions each.

The COD10K dataset is currently the largest challenging dataset for COD, containing 10K images with dense annotations.

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 dataset used in this paper for medical image segmentation, including images from the ISBI-2012 dataset.

Multi-label image recognition is a practical and challenging task compared to single-label image classification.

The dataset used in the paper is a set of images from the AFHQ dataset, containing 1.5K images of different animal faces.

Multi-task learning (MTL) research is broadly divided into two categories: one is to learn the correlation between tasks through model structures, and the other is to balance...

Oxford 102 Flowers is a dataset of images of different flower species.

The dataset used in this paper is the Meta Research's Segment Anything Model (SAM) dataset, which consists of images.

Semantic segmentation is a crucial and challenging task for image understanding. It aims to predict a dense labeling map for the input image, which assigns each pixel a unique...

RGB-D scene recognition approaches often train two standalone backbones for RGB and depth modalities with the same Places or ImageNet pre-training. However, the pre-trained...

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...