34 datasets found

The proposed Tracking-by-Animation (TBA) framework achieves unsupervised end-to-end learning of MOT tasks.

The dataset used in the paper for unsupervised domain adaptation.

Unsupervised deep image stitching: Reconstructing stitched features to images.

Chinese–Japanese Unsupervised Neural Machine Translation Using Sub-character Level Information

Unsupervised domain generalization (UDG) aims to learn generalizable models with unlabeled data and analyze the effects of pre-training on DG.

Synthetic Aperture Sonar (SAS) images, semi-labeled (i.e. not every pixel is labeled in every image)

RF PIX2PIX Unsupervised Wi-Fi to Video Translation

Reliable fault detection is an essential requirement for safe and efficient operation of complex mechanical systems in various industrial applications.

A benchmark dataset for few-shot image-to-image translation

Birds dataset consists of 28752 images of birds, each described by a Fisher vector representation.

A benchmark dataset for few-shot image-to-image translation

A benchmark dataset for few-shot image-to-image translation

Few-shot unsupervised image-to-image translation with a content conditioned style encoder

This paper proposes the Davis 2017 validation set for video object segmentation.

The Brain Image Synthesis with Unsupervised Multivariate Canonical Correlation Analysis (CSCL4Net) dataset is used to evaluate the performance of brain image synthesis algorithms.

ChangeChip is a comprehensive system for detecting defects on PCBs by applying change detection.

The proposed approach is tested on English-German, English-French and Chinese-to-English translation tasks.

Training a model for grammatical error correction (GEC) requires a set of labeled ungrammatical / grammatical sentence pairs, but manually annotating such pairs can be expensive.

The ImageCLEF-DA dataset is a benchmark dataset for ImageCLEF 2014 domain adaptation challenges, which contains 12 categories shared by three domains: Caltech-256 (C), ImageNet...

UCR Time Series Archive is a collection of time series datasets from various domains. It is used for training and testing deep neural networks for time series classification tasks.