93 datasets found

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 PASCAL-Context dataset comprises 4,998 images for training and 5,105 images for testing. This dataset offers dense labels for four tasks including semantic segmentation,...

The Segment Anything Model (SAM) has been proven to be a powerful foundation model for image segmentation tasks, which is an important task in computer vision. However, the...

The dataset used in the paper is a pre-trained ResNet-50 classifier, which is used for image synthesis, unpaired image-to-image translation, and feature similarity estimation.

A dataset of textual entailment tasks, used for evaluating the ability of language models to understand relationships between texts.

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

Scene segmentation in images is a fundamental yet challenging problem in visual content understanding, which is to learn a model to assign every image pixel to a categorical label.

The PASCAL VOC2007 dataset is a benchmark for object detection and image classification.

The RefCOCOg dataset is a reconstructed dataset of the MS-COCO dataset, containing 85,474 referring expressions for 54,822 objects in 26,711 images.

The dataset used in the paper is a benchmark for referring expression grounding, containing 142,210 referring expressions for 50,000 referents in 19,994 images.

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...

Publicly available plant image datasets are crucial in precision agriculture as they reduce the time and effort spent on data collection and preparation. Also, more data enable...

A dataset of 42 breast ultrasound images acquired by Shantou University using the GE Voluson E10 ultrasonic diagnostic system.

The dataset used in the paper is a collection of digital breast tomosynthesis (DBT) stacks with masses inserted in the center of the stack.

The BUSI dataset is a collection of ultrasound images depicting normal, benign, and malignant breast cancer cases along with their corresponding segmentation maps.

Three public breast ultrasound datasets (BUSI, Dataset B, and STU) are used to evaluate the segmentation network performance.

From image-level to pixel-level labeling with convolutional networks.

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...

The dataset used in the paper is a synthetic dataset for blind super-resolution, consisting of low-resolution images and their corresponding blur kernels.