-
CIFAR10, CIFAR100, STL10, ImageNet
The dataset used in this paper for image classification and object detection tasks. -
The Caltech-UCSD Birds-200-2011 Dataset
The CUB dataset is a collection of images of landbirds and waterbirds from the CUB dataset, combined with images from Places dataset as background. -
DetNAS: Backbone Search for Object Detection
Object detectors are usually equipped with backbone networks designed for image classification. It might be sub-optimal because of the gap between the tasks of image... -
Hazy-COCO dataset
The Hazy-COCO dataset is a synthetic dataset generated by adding haze to the MS COCO dataset. -
YOLO-Former: YOLO Shakes Hand With ViT
The proposed YOLO-Former method seamlessly integrates the ideas of transformer and YOLOv4 to create a highly accurate and efficient object detection system. -
Stanford Drone Dataset
The Stanford Drone Dataset is a well-established benchmark for human trajectory prediction in bird’s eye view. The dataset consists of 20 scenes captured using a drone in... -
RefCOCO dataset
The authors used the RefCOCO dataset, a large-scale dataset for object detection and scene understanding, to train and evaluate their models. -
DiffusionDet: Diffusion Model for Object Detection
DiffusionDet is a new framework that formulates object detection as a denoising diffusion process from noisy boxes to object boxes. -
SSD: Single Shot Multibox Detector
SSD is a single-shot object detection algorithm. -
Feature Selective Networks for Object Detection
Objects for detection usually have distinct characteristics in different sub-regions and different aspect ratios. However, in prevalent two-stage object detection methods,... -
PASCAL VOC, COCO, TJU-DHD, and ImageNet datasets
The dataset used in the paper for object detection, featuring images from PASCAL VOC, COCO, TJU-DHD, and ImageNet. -
MS COCO dataset
The MS COCO dataset is a large benchmark for image captioning, containing 328K images with 5 caption descriptions each. -
ImageNet: A Large-Scale Hierarchical Image Database
The ImageNet dataset is a large-scale image database that contains over 14 million images, each labeled with one of 21,841 categories. -
COCO+LVIS dataset
The COCO+LVIS dataset contains millions of high-quality labels for natural images. -
Galaxy Zoo
The Galaxy Zoo dataset is used to test the ability of TARGET-VAE to predict rotation and translation of objects in images. -
Inria dataset
The Inria dataset is a dataset of images used for object detection tasks. -
Inria-Patch dataset
The Inria-Patch dataset is a dataset of adversarial patches generated using the attack method [14] to defend against patch attacks in human detection systems. -
COD10K, CHAMELEON, CAMO, ISTD, kvasir-SEG
The dataset used for camouflaged object detection, shadow detection, and polyp segmentation tasks.
