124 datasets found

The PASCAL Visual Object Classes Challenge (VOC) is a benchmark dataset for object detection and semantic segmentation.

Incremental learning techniques for semantic segmentation

The dataset used in the paper is a synthetic dataset for image-based object detection tasks, specifically instance segmentation and monocular 3D detection.

The dataset used for out-of-distribution segmentation, zero-shot semantic segmentation, and domain adaptation.

SemanticKITTI: A dataset for semantic scene understanding of lidar sequences.

Semantic segmentation of point clouds is a key component of scene understanding for robotics and autonomous driving. In this paper, we introduce TORNADO-Net - a neural network...

A dataset for sewer-culvert defect segmentation, featuring pixel-level annotations of nine common structural deficiency classes.

The NYU dataset contains 1449 depth maps captured by Kinect.

The SUNCG dataset is a manually created large-scale synthetic scene dataset. It contains 139368 valid pairs of depth map and complete labels for training, and 470 pairs for...

A novel road rutting dataset containing 949 images from heterogeneous sources.

Semantic segmentation performs pixel-level classifica- tion to localize objects from different classes in the input image. Open-vocabulary semantic segmentation aims to...

Remote sensing image segmentation is a critical research area within remote sensing image processing. Its primary objective is to divide remote sensing imagery into separate...

The dataset used for training and testing the proposed RGBD-based obstacle avoidance system for visually impaired people.

Semantic segmentation is a fundamental task in many computer vision applications, which assigns a class label to each pixel in the image.

Real-time semantic segmentation is playing a more important role in computer vision, due to the growing demand for mobile devices and autonomous driving. Therefore, it is very...

The ADE20K dataset is a large-scale dataset for semantic segmentation. It contains 20,000 images with 150 semantic categories, with 20,000 images for training, 2,000 images for...

The NYUv2 dataset is a large-scale dataset for 3D object recognition and semantic segmentation. It contains 206 test set video sequences with 135 classes.

Anomaly detection in semantic segmentation

The SBD dataset is a benchmark dataset for semantic segmentation and object detection.

Dark Zurich is a dataset for nighttime semantic segmentation. It contains daytime reference images and nighttime images with corresponding annotations.