361 datasets found

The dataset used in this paper is the Focal Loss for dense object detection.

The dataset used in this paper is the Faster R-CNN object detector.

The dataset used in this paper is the Microsoft COCO 2014 dataset.

The dataset used in this paper is the Faster R-CNN and RetinaNet object detectors.

Single Shot MultiBox Detector.

The VisDrone dataset is a large-scale dataset for object detection in aerial images.

Audio-visual segmentation (AVS) aims to segment sound sources in the video sequence, requiring a pixel-level understanding of audio-visual correspondence.

Fine-grained image classification, which aims to recognize subordinate level categories, has emerged as a popular research area in the computer vision community.

Convolutional Neural Networks (CNNs) have achieved great success due to the powerful feature learning ability of convolution layers. Specifically, the standard convolution...

ABOSHIPS - AN INSHORE AND OFFSHORE MARITIME VESSEL DETECTION DATASET WITH PRECISE ANNOTATIONS

BDD-100k dataset

A universal targeted label-switch patch that changes an OD's detection of car on which it is applied, from the correct target class (car) to a bus.

Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories

FSOD is a benchmark for object-level image retrieval, containing 14K images from 200 categories.

Few-shot Object Detection dataset

The dataset used in the paper is the Alibaba Tianchi competition: Alibaba-Tsinghua Adversarial Challenge on Object Detection.

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 proposed DualConv is used to replace the standard convolution in VGG-16 and ResNet-50 to perform image classification experiments on CIFAR-10, CIFAR-100, and ImageNet datasets.

The ImageNet object detection dataset, which contains a sufficiently large number of images and object categories to reach a conclusion.

Places205 is a dataset of 2.5 million images from 205 categories, with 12,000 images per category.