-
ImageNet2012
The dataset used in the paper for attention-oriented data analysis and attention-based adversarial defense. -
Mask-guided Vision Transformer for Few-Shot Learning
The proposed MG-ViT model is used for few-shot learning on the Agri-ImageNet and ACFR apple detection tasks. -
Selective Search for Object Recognition
Selective search is a method for object detection. -
OpenImagesV4 Dataset
The OpenImagesV4 dataset is a large benchmark dataset for object detection and image classification. It contains 1.7 million images with 1,000 object classes. -
PASCAL VOC 2007, 2010, 2012, ILSVRC 2013, and MSCOCO 2014 datasets
The PASCAL VOC 2007, 2010, 2012 datasets, the ILSVRC 2013 dataset, and the MSCOCO 2014 dataset. -
PASCAL VOC Dataset
The PASCAL VOC dataset contains 20 classes, including person, animal, vehicle, and indoor, with 9,963 images containing 24,640 annotated objects. -
Microsoft COCO: common objects in context
The COCO dataset is a large-scale dataset for object detection and image classification. -
Linley et al. (2014) - Microsoft COCO
Linley et al. (2014) - Microsoft COCO -
iNaturalist-18/19
The dataset used in the paper is iNaturalist-18/19, a dataset for object detection and image classification. -
iNaturalist 2018 and iNaturalist 2019
The dataset used in the paper is iNaturalist 2018 and iNaturalist 2019, two datasets for object detection and image classification. -
FGVC Aircraft
The FGVC Aircraft dataset is a dataset of images of aircraft, where each image is classified into one of 100 categories. -
CAE v2: Context Autoencoder with CLIP Target
Masked image modeling (MIM) learns visual representation by masking and reconstructing image patches. Applying the reconstruction supervision on the CLIP representation has been... -
Microsoft COCO Dataset
The MS COCO 2014 Dataset contains images of 91 object categories, which contains 82783 training images, 40504 validation images and 40775 testing images. -
Stanford Cars dataset
The Stanford Cars dataset is a dataset of images of cars, with 196 categories and approximately 16,000 images. The authors created a synthetic dataset by adding occlusions of... -
Inter-Instance Similarity Modeling for Contrastive Learning
The existing contrastive learning methods widely adopt one-hot instance discrimination as pretext task for self-supervised learning, which inevitably neglects rich... -
Cars Overhead With Context (COWC) dataset
The dataset used in the paper is the Cars Overhead With Context (COWC) dataset, which contains images of cars in overhead imagery. -
Open Images
The Open Images dataset is a large-scale image dataset with a wide range of images, including but not limited to, street scenes, indoor scenes, and outdoor scenes. -
ESD dataset
The ESD dataset offers finetuned weights for the 'car' and 'French-horn' classes.
