150 datasets found

Semantic segmentation tasks naturally require high-resolution information for pixel-wise segmentation and global context information for class prediction.

University of Pavia is a popular benchmark dataset for semantic segmentation.

DeepLab v2 is a state-of-the-art semantic segmentation model.

Satellite images are an extremely valuable resource in the aftermath of natural disasters such as hurricanes and tsunamis where they can be used for risk assessment and disaster...

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 large-scale point cloud classification benchmark, focusing on semantic segmentation of urban scenes.

Active domain adaptation has emerged as a solution to balance the expensive annotation cost and the performance of trained models in semantic segmentation.

The proposed framework for leveraging the semantic segment without transferring any extra bit.

The SemanticKITTI dataset is a LiDAR-based semantic segmentation dataset, which consists of 10 sequences for training and 1 for validation.

CelebAMask-HQ provides the parsing map of images in CelebA-HQ down-sampled to 512 × 512, where pixel-level annotation of 19 classes, including facial components and accessories,...

The dataset is used for indoor scene understanding and contains RGB and depth images.

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

Semantic segmentation benchmarking framework with decoupled design for feature extraction and decoding methods.

The proposed ClassWise-SAM-Adapter (CWSAM) is designed to adapt the high-performing SAM for landcover classification on space-borne Synthetic Aperture Radar (SAR) images.

The proposed learnable tree filter for structure-preserving feature transform.

The dataset used in the paper is COCO-Stuff, Pascal-VOC, and Pascal-Context. COCO-Stuff is an extensive semantic segmentation dataset comprising 171 categories, encompassing 80...

The dataset used for large-vocabulary semantic segmentation, including ADE20K, Cityscapes, and COCO-Stuff.

The dataset used in the paper is DeepLabV3 dataset.

The dataset used in the paper is ImageNet, MS COCO, and Pascal VOC datasets.

The dataset used in the paper is Argoverse-HD, Cityscapes, and nuScenes.