246 datasets found

The dataset used for histopathology image segmentation and classification.

The LoveDA dataset contains high-spatial-resolution images from three different cities, focusing on improving the generalization capability of model from different urban and...

Vehicle detection in real-time is a challenging and important task. The existing real-time vehicle detection lacks accuracy and speed. Real-time systems must detect and locate...

The ISPRS Vaihingen dataset consists of remotely sensed imagery with a spatial resolution of 9 centimeters, and includes 6 semantic classes.

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...

DeepSynth: Three-dimensional nuclear segmentation of biological images using neural networks trained with synthetic data.

The PhraseCut dataset contains images annotated with referring expressions, focusing on phrases with a single entity and relation.

Visual Grounding is a task that aims to locate a target object according to a natural language expression. The dataset used in this paper is RefCOCO, RefCOCO+, and RefCOCOg.

The NYUDv2 dataset contains 1,449 labeled indoor-scene RGB images with both parsing annotations and Kinect depths.

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...

The probabilistic atlas dataset, which includes MRI scans of 20 subjects.

The dataset used for the proposed Segmentation Auto-Encoder (SAE) method for adaptive image segmentation.

The COCO dataset is a large-scale dataset for object detection, semantic segmentation, and captioning. It contains 80 object categories and 1,000 image instances per category,...

The FSS-1000 dataset contains 1000 images with 1000 object categories.

The Visual Genome dataset is a large-scale visual question answering dataset, containing 1.5 million images, each with 15-30 annotated entities, attributes, and relationships.

Semantic segmentation is one of the fundamental prob-lems in computer vision, whose task is to assign a seman-tic label to each pixel of an image so that different classes can...

The GTA5→Cityscapes dataset is a synthetic-to-real benchmark dataset for domain adaptation in semantic segmentation.

The Sewer Pipe Cracks dataset contains images of sewer pipes with and without cracks.

The Magnetic Tile Defect Datasets contain images of magnetic tiles with and without defects.

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...