20 datasets found

The dataset used in the paper is Amazon clothing, Amazon-Electronics, and DBLP.

Few-shot part segmentation for 3D shapes

A few-shot personalized conversation task with an auxiliary social network, catering for low-resource speakers.

SCAN is a semantic parsing dataset of natural language navigation commands that are mapped to corresponding action sequences.

miniImageNet, tieredImageNet, Caltech-USCD birds-200-2011

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used the Mini-Imagenet and CIFAR-FS datasets for few-shot learning tasks.

Few-shot segmentation remains challenging due to the limitations of its labeling information for unseen classes. Most previous approaches rely on extracting high-level feature...

The CIFAR-FS dataset is a few-shot learning dataset, consisting of 60,000 color images from 100 classes with 600 examples per class.

The miniImagenet and tieredImageNet datasets are used for few-shot classification experiments.

Few-shot semantic segmentation via prototype augmentation with image-level annotations

PartImageNet and Pascal Part datasets for few-shot part segmentation.

Few-shot part segmentation using few-shot support images and pre-trained image-language model CLIP.

Knowledge distillation with few samples and black-box teacher. The method uses MixUp and Conditional Variational Autoencoder (CVAE) to generate synthetic images to train the...

The Paderborn University (PU) dataset is used to evaluate the proposed Multi-Scale Graph Convolution Filtering (MSGCF) method for few-shot fault diagnosis in industrial...

Fine-Grained Visual Classification (FGVC) is an important computer vision prob-lem that involves small diversity within the different classes, and often requires expert...

CUB-200 is a fine-grained image classification dataset containing high resolution images of 200 different bird species.

DeepFashion2 is a large-scale fashion image benchmark with comprehensive tasks and annotations. It contains 491K images, each of which is richly labeled with style, scale,...

Few-shot keypoint detection (FSKD) attempts to localize any keypoints, including novel or base keypoints, depending on the reference samples.

Few-shot keypoint detection (FSKD) attempts to localize any keypoints, including novel or base keypoints, depending on the reference samples.

Few-shot keypoint detection (FSKD) attempts to localize any keypoints, including novel or base keypoints, depending on the reference samples.