-
MIT Places2
MIT Places2 is a scene-centric dataset with more than 10 million images consisting of over 400 unique scene classes. -
FGVC Aircraft (Airplanes)
FGVC Aircraft (Airplanes) contains 102 different aircraft model variants with 100 images of each. -
Oxford 102 Flowers
Oxford 102 Flowers is a dataset of images of different flower species. -
Caltech-UCSD Birds (CUB) 200-2011
Caltech-UCSD Birds (CUB) 200-2011 is a frequently used benchmark for unsupervised image segmentation. It consists of 11,788 images from 200 bird species. -
Coco: Common objects in context
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... -
Syntagen - Harnessing Generative Models for Synthetic Visual Datasets
The dataset is generated using a latent diffusion model, specifically Stable Diffusion 2.1, and is used for semantic segmentation tasks. -
ISPRS Potsdam
The ISPRS Potsdam dataset consists of remotely sensed imagery with a spatial resolution of 5 centimeters, and includes 6 semantic classes. -
AAU-net: An Adaptive Attention U-net for Breast Lesions Segmentation in Ultra...
Three public breast ultrasound datasets (BUSI, Dataset B, and STU) are used to evaluate the segmentation network performance. -
Segment Anything Model
The dataset used in this paper is the Meta Research's Segment Anything Model (SAM) dataset, which consists of images. -
From Image-Level to Pixel-Level Labeling with Convolutional Networks
From image-level to pixel-level labeling with convolutional networks. -
Bitewing Radiography Semantic Segmentation
This dataset is used for semantic segmentation of bitewing radiography images. The goal is to segment the images into caries, enamel, dentin, pulp, crowns, restoration and root... -
MS COCO 2014
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... -
ISPRS Vaihingen
The ISPRS Vaihingen dataset consists of remotely sensed imagery with a spatial resolution of 9 centimeters, and includes 6 semantic classes. -
Pascal VOC
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...
