65 datasets found

Crowd counting has drawn increasing attention because of its fundamental role in social management. Six datasets are used in our experiments, i.e., GCC, ShanghaiTech PartA,...

Real-world domain adaptation dataset for spam detection, which was released as part of the ECML PKDD 2006 Discovery Challenge.

Synthetic regression problem with two users attempting to fit a linear model of the function f (x1, x2) = 5x1 − 2x2 + 0.5x3^2. Each user has input data drawn from a distinct...

The dataset used in the paper for sentiment analysis in cross-language and cross-domain settings.

A semi-supervised active domain adaptation framework for semantic segmentation in driving scenes.

The dataset used for extensive cut-and-paste augmentation for unsupervised domain adaptive semantic segmentation.

The dataset used for unsupervised domain adaptation for semantic segmentation with pseudo label self-refinement.

The dataset used in the paper for domain adaptation for sustainable soil management using causal and contrastive constraint minimization.

The dataset used for the proposed Joint Multi-Domain Learning for Automatic Short Answer Grading.

The dataset used for sim-to-real domain adaptation in robotics, consisting of tasks with randomized dynamics.

The dataset used in this paper for unsupervised domain adaptation.

Change detection is a crucial but extremely challenging task in remote sensing image analysis, and much progress has been made with the rapid development of deep learning....

Select-by-Distinctive-Margin (SDM) is a simple yet effective active learning method for active domain adaptation.

The Office-31 dataset is a benchmark dataset for domain adaptation, containing images from the Amazon domain.

The Office+Caltech-10 dataset is a benchmark dataset for domain adaptation, combining Office-10 and Caltech-10 datasets.

Generating artistic portraits is a challenging problem in computer vision. Existing portrait stylization models that generate good quality results are based on Image-to-Image...

Unsupervised domain adaptation studies the problem of utilizing a relevant source domain with abundant labels to build predictive modeling for an unannotated target domain.

The proposed method is implemented by the Pytorch framework using a NVIDIA GeForce RTX 3090 GPU with 24GB memory.

The PointDA-10 dataset consists of three subsets of three widely-used datasets: ShapeNet, ModelNet, and ScanNet. All three subsets share the same ten distinct classes.

The Synthia dataset is a large-scale urban scene understanding dataset, containing 9000 samples. It is used for semantic segmentation tasks.